Ege is available for hire
Hire EgeEge Hakan Karaağaç
Verified Expert in Engineering
Full-stack AI Developer
Istanbul, Turkey
Toptal member since June 29, 2026
Bio
Ege is a full-stack AI engineer who builds the whole product, from retrieval and agents to the React dashboard and the AWS infrastructure it runs on. As Founding Engineer of BrandVox AI, he shipped a multitenant AI SaaS solo to paying customers across 5 services: a FastAPI back end, a forked agent engine, an embeddable widget, and real-time voice. Before that, Ege built back-end systems at Amazon and Dream Games. He treats evals and cost control as first-class, not afterthoughts.
Portfolio
Legaltech SaaS Company (Corporate Governance)
TypeScript, Node.js, Bun, Hono, oRPC, Zod, Drizzle ORM, PostgreSQL...
US Legal-tech Startup
Python, Node.js, MongoDB, Pinecone, REST APIs, OpenAI API, WordPress...
BrandVox AI
Python 3, FastAPI, Artificial Intelligence (AI)...
Experience
- Python 3 - 7 years
- Amazon Web Services (AWS) - 5 years
- Artificial Intelligence (AI) - 4 years
- FastAPI - 4 years
- AI Agents - 3 years
- Retrieval-augmented Generation (RAG) - 3 years
- Large Language Models (LLMs) - 3 years
- LangChain - 3 years
Work Experience
Full-stack AI Engineer (Contract)
2026 - PRESENT
Legaltech SaaS Company (Corporate Governance)
- Developed the product’s AI platform from scratch in a TypeScript monorepo: a durable tool-calling agent on Vercel AI SDK, running Claude on Amazon Bedrock, with tenant-scoped tools and resumable streaming responses.
- Built a durable workflow engine that drafts documents, collects e-signatures, and records outcomes across dozens of client entities in a single run, with human sign-off before any change is committed.
- Re-architected the engine into per-entity child workflows to remove replay failures at scale, then validated it with a 50-entity soak test that ran clean and survived a worker crash without losing state.
- Introduced PostgreSQL row-level security for tenant isolation, plus layered AI safety controls: prompt-injection defenses, output PII scanning, guardrails, and rate and budget limits with a usage ledger.
- Built a hybrid RAG over legal documents: text extraction, vector embeddings fused with full-text search via reciprocal rank fusion, cited answers, and durable ingestion with a dead-letter queue.
- Developed an AI document reviewer that proposes tracked-change redlines inside the real-time collaborative editor, plus jurisdiction-aware compliance checks using structured outputs.
- Shipped full-stack product features in Next.js and TypeScript, from guided setup flows and AI summaries to chat history and exports, working across the API, database, and UI.
- Built an LLM-as-judge eval suite with release thresholds and adversarial fixtures (cross-tenant leakage, poisoned documents), plus privacy-safe LLM telemetry for cost and latency.
- Deployed the AI services to AWS ECS Fargate with Terraform and debugged production-only failures from CloudWatch evidence, across 50+ merged product PRs and 15 infrastructure PRs.
Technologies: TypeScript, Node.js, Bun, Hono, oRPC, Zod, Drizzle ORM, PostgreSQL, Transport Layer Security (TLS), Row-level Security (RLS), Pgvector, Full-text Search, Vercel, Workflow, DevKit, Durable Execution Workflows, Amazon Bedrock AgentCore, Claude, Claude API, Cohere, Artificial Intelligence (AI), Generative Artificial Intelligence (GenAI), Large Language Models (LLMs), AI Agents, Agentic AI, Agentic AI Systems, AI Agent Orchestration, Function Calling, Prompt Engineering, Retrieval-augmented Generation (RAG), RAG Systems, Hybrid Search, Embedding Models, Semantic Search, Vector Search, Human-in-the-loop (HITL), Evaluation, AI Model Integration, AI Integration, LLM Integration, AI Architecture, AI Engineering, AI Chatbots, Chatbots, Conversational AI, Legal Technology (Legaltech), Document Processing, Data Extraction, Data Pipelines, Workflows, Workflow Automation, Event-driven Systems, Server Sent Events (SSE), Streaming, WebSockets, Real-time Data, Next.js, React, Tailwind CSS, Radix UI, Shadcn UI, TanStack Table, Front-end, Front-end Development, Web Applications, OpenTelemetry, PostHog, Privacy, Security, Application Security, Web Security, Role-based Access Control (RBAC), Multitenancy, Multi-tenant SaaS, Software as a Service (SaaS), Amazon Web Services (AWS), AWS ECS Fargate, Amazon Elastic Container Service (ECS), Load Balancers, AWS ALB, AWS IAM, AWS Secrets Manager, Amazon RDS, Amazon S3 (AWS S3), Amazon CloudWatch, Amazon Elastic Container Registry (ECR), Terraform, Terragrunt, Docker, GitHub Actions, Continuous Integration (CI), CI/CD Pipelines, DevOps, Release Management, Playwright, Vitest, Turborepo, Monorepos, Database Migration, Data Modeling, Resend, Email, Linear, Claude Code, Agentic Coding, Debugging, Performance, Optimization, System Optimization, Scalability, Solution Architecture, Software Architecture, System Architecture, Technical Leadership, Third-party APIs, API Integration, API Design, REST APIs, Back-end, Full-stack, Full-stack Development, Business Process Automation, Entity Relationships, CSV, Reporting, Cost Estimation, Server-side PDF Generation, Security Audits, IT Deployments, AI Project Management, Third-party Integration, Document Parsing, Data Processing, Back-end Development, Product Management
Senior Full-stack AI Engineer (via Toptal)
2026 - PRESENT
US Legal-tech Startup
- Took over an undocumented production system (FastAPI, MongoDB, Pinecone and OpenAI on AWS EC2) from a departing contractor, recovered the only current code and data with verified restores, and ran the offboarding.
- Ran a security audit and lockdown of the live platform: closed an SSH path that survived IAM revocation and exposed ports, put the admin dashboard behind TLS and an authenticated proxy, and moved credentials to least-privilege IAM.
- Architected and built the rebuild on Next.js 16, TypeScript and Supabase Postgres: 82 migrations with row-level security on every table, role-based access, a hash-chained audit ledger and a hard attorney-approval gate.
- Built GPT-5 contract drafting and review pipelines with versioned prompts, strict JSON-schema outputs, PDF/DOCX export and a per-call cost ledger, tested with 120 recorded replay fixtures so CI never spends API money.
- Built a paid attorney-review workflow (quote, engagement letter, signature, Stripe Checkout, signed webhooks), an OAuth 2.1 MCP server with 23 content tools that connects the knowledge base to Claude, and a rich-text content editor for staff.
- Migrated 107 templates and 282 articles with pgvector embeddings, built the SEO layer, and set up Railway, Terraform, Docker and GitHub Actions CI/CD, covered by 163 unit test files, 64 Playwright specs and 1,832 DB assertions.
- Shipped attorney-review email alerts (Resend) to the live system with pytest coverage and a rollback plan, and gave the founder architecture options, hosting-cost models at 1x/10x/100x traffic and bottom-up estimates.
Technologies: Python, Node.js, MongoDB, Pinecone, REST APIs, OpenAI API, WordPress, Workflow Automation & System Integration, RAG Systems, GitHub, Back-end Architecture, Debugging, Full-stack Development, FastAPI, Next.js, React, TypeScript, Tailwind CSS, Shadcn UI, Radix UI, Supabase, Supabase Auth, PostgreSQL, Row-level Security (RLS), Pgvector, Role-based Access Control (RBAC), Python 3, Pytest, OpenAI, Generative Pre-trained Transformers (GPT), Artificial Intelligence (AI), Generative Artificial Intelligence (GenAI), Large Language Models (LLMs), AI Model Integration, AI Integration, LLM Integration, Prompt Engineering, Retrieval-augmented Generation (RAG), Embedding Models, Semantic Search, Evaluation, AI Chatbots, Model Context Protocol (MCP), OAuth, Server-side PDF Generation, Legal Technology (Legaltech), Stripe, Payment APIs, Webhooks, Resend, Email, Security, Application Security, Web Security, Security Audits, Incident Response, Privacy, Amazon Web Services (AWS), Amazon EC2, Amazon S3 (AWS S3), AWS IAM, NGINX, Transport Layer Security (TLS), Let's Encrypt, Linux, Server Administration, Railway, Terraform, Docker, GitHub Actions, Continuous Integration (CI), CI/CD Pipelines, DevOps, IT Deployments, Playwright, Vitest, Turborepo, Monorepos, Database Migration, Data Migration, Data Modeling, Content Management Systems (CMS), Accessibility, Front-end, Web Applications, Server-side Rendering (SSR), Multi-tenant SaaS, Solution Architecture, Software Architecture, System Architecture, Technical Leadership, Technical Project Management, AI Project Management, Cost Estimation, Vendor Management, Third-party APIs, Third-party Integration, API Integration, RESTFul APIs, Back-end, Full-stack, Claude Code, Agentic Coding, Data Pipelines, Data Extraction, AI Architecture, Chatbots, Document Processing, Front-end Development, Software as a Service (SaaS), Release Management, System Optimization, Document Parsing, Data Processing, Back-end Development, Product Management
Founding Engineer | CEO
2024 - PRESENT
BrandVox AI
- Architected a multitenant AI SaaS solo, from zero to 1,000+ users and 30+ paying customers across 5 services (around 1,557 commits, dominant author), led by an around 90,000-LOC FastAPI back end and a forked Flowise agent engine.
- Built a hybrid retrieval in the forked Flowise engine: Qdrant dense vectors fused with BM25 sparse through a custom Reciprocal Rank Fusion ranker, with a weighted 0.7/0.3 ensemble live in production and RRF switchable.
- Built a multi-provider generation layer (OpenAI, Anthropic, Gemini, Grok) with cascading fallback so generation does not fall over when a provider does, plus provider routing and credit-based per-model cost accounting.
- Shipped a real-time voice pipeline over WebSockets (OpenAI Realtime API, PCM16/24kHz, server VAD, barge-in) with exactly-once turn persistence, plus image and video generation through Fal.ai.
- Built a Qdrant-versus-DynamoDB orphan-reconciliation garbage collector (dry-run gate) to keep vectors consistent after distributed deletes, with agentic tool-calling, structured outputs, and prompt-injection handling.
- Ran the platform solo on AWS ECS Fargate behind an ALB (39 DynamoDB tables, Redis/MemoryDB, Elasticsearch for chat/lead search, S3, Cloudflare), with Terraform, GitHub Actions, and Sentry, Grafana, PostHog, and CloudWatch.
Technologies: Python 3, FastAPI, Artificial Intelligence (AI), Retrieval-augmented Generation (RAG), Hybrid Search, Qdrant, Vector Databases, Okapi BM25, Vector Search, Reciprocal Rank Fusion, OpenAI API, Claude API, Gemini API, AI Agent Orchestration, AI Agents, Agentic Workflow Design, Tool Calling, Prompt Engineering, OpenAI Realtime API, Server Sent Events (SSE), WebSockets, Server VAD, Fal.ai, LangChain, Flowise, Model Context Protocol (MCP), Multi-tenant SaaS, Node.js, TypeScript, React, Next.js, Amazon DynamoDB, Redis, Elasticsearch, Amazon S3 (AWS S3), Amazon Elastic Container Service (ECS), AWS ECS Fargate, Amazon EC2, Terraform, GitHub Actions, Cloudflare, Sentry, Grafana, PostHog, Amazon CloudWatch, Multimodal GenAI, Multimodal Models, Apollo.io, Embedding Models, RAG Systems, Semantic Search, Pgvector, Re-ranking, Chunking, Generative Artificial Intelligence (GenAI), Human-in-the-loop (HITL), SQL Injection Protection, LangGraph, Claude Code, AI Engineering, Machine Learning, Model Agnostic Development, LLM Evals, LLM-as-Judge, Evaluation, Per-token Cost Metering, Realtime Voice AI, Multimodel AI, Image Generation, Video Generation, JavaScript, Large Language Models (LLMs), Natural Language Processing (NLP), Pinecone, Weaviate, Agentic AI, Agentic AI Systems, Function Calling, Conversational AI, AI Chatbots, AI Integration, LLM Integration, OpenAI, ChatGPT, Anthropic, Claude, Gemini, Generative Pre-trained Transformers (GPT), Large Language Model Operations (LLMOps), CSS, Tailwind CSS, Shadcn UI, Amazon Web Services (AWS), AWS Lambda, AWS IAM, Docker, Google Analytics, Google Search Console, Linux, PostgreSQL, Databases, Database Migration, Database Architecture, Distributed Systems, Microservices, Event-driven Architecture, Low-latency Software, Idempotency, REST APIs, Git, JSON Web Tokens (JWT), Algorithms, Data Structures, Programming Languages, Software Engineering, Object-oriented Programming (OOP), Agent Orchestration, Keyword Searches, Back-end, Full-stack, Full-stack Development, Web Development, APIs, API Development, API Design, API Integration, API Documentation, RESTFul APIs, Real-time Data, Scalability, Migration, Data Modeling, Data Architecture, NoSQL, Authentication, Multitenancy, JSON, XML, GitHub, Architecture, Software Architecture, System Architecture, Cloud Architecture, Cloud Infrastructure, System Integration, Integration, Agentic RAG Systems, AI Tools, AI Product Strategy, Agentic Coding, Workflow Automation, Minimum Viable Product (MVP), B2C, User Experience (UX), User Interface (UI), Design, Communication, Stripe, Stripe Connect, Single Sign-on (SSO), Python, Amazon Bedrock AgentCore, AI Automation, Structured Outputs, Generator-Evaluator, Streaming, LangSmith, Playwright, Pydantic, APScheduler, Async.js, Web Crawlers, Web Scraping, Data Scraping, Facebook SDK, Facebook, Facebook API, CRM, Multi-agent Orchestration, Workflow, Workflows, Multi-agent Systems, Automation, Integrations, Reviews, Security, Back-end Architecture, Debugging, Workflow Automation & System Integration, Front-end, LLM Agents, API Management, Event-driven Design (EDD), Business Process Automation, Radix UI, Framer Motion, AI Model Integration, Data Pipelines, Data Extraction, Data Integration, Data Engineering, Entity Relationships, B2B Lead Generation, Third-party APIs, CSV, Reporting, Web Applications, Solution Architecture, Technical Project Management, Vendor Management, Cost Estimation, Role-based Access Control (RBAC), Pytest, OAuth, Payment APIs, Webhooks, Email, Application Security, Web Security, Incident Response, Privacy, NGINX, Continuous Integration (CI), CI/CD Pipelines, DevOps, IT Deployments, Data Migration, Content Management Systems (CMS), Accessibility, Server-side Rendering (SSR), Technical Leadership, AI Project Management, Third-party Integration, Full-text Search, Durable Execution Workflows, AI Architecture, Chatbots, Document Processing, Event-driven Systems, Front-end Development, Software as a Service (SaaS), Load Balancers, AWS ALB, AWS Secrets Manager, Amazon Elastic Container Registry (ECR), Release Management, Linear, Performance, System Optimization, Optimization, Document Parsing, Data Processing, Gmail, Back-end Development, Product Management
AI Engineer (via Toptal)
2026 - 2026
Totemic Padel Holdings, Inc.
- Built and deployed an AI lead-generation agent that finds, verifies and ranks investors for a new US sports-facility venture, going from a pre-interview prototype to a deployed tool in about two weeks.
- Designed a six-stage LangGraph.js pipeline (discover, resolve, score in parallel, human review, enrich, load) with bounded LLM concurrency, streamed run progress, single-run locking and re-attachable runs.
- Integrated six data sources through APIs (Tavily search and extract, SEC EDGAR Form D full-text search, Apollo.io, Apify LinkedIn profiles, Claude) with response caching and graceful degradation when a key is missing.
- Used Claude with strict tool schemas to extract intent signals, kept only those quoted verbatim in the source, scored leads 0-100 on six weighted factors, and verified contacts through an LLM-judged funnel.
- Built a Next.js 16 dashboard with cited evidence per lead, a live run timeline with a cost meter, and a CRM-ready CSV export, on Prisma and Supabase Postgres, deployed on Railway.
- Ran discovery and delivery end to end: a spec response with build-vs-buy advice on data vendors, a five-milestone plan, a running-cost model, and a documented handover of all accounts; the client ran it repeatedly and worked 120+ leads from it.
Technologies: AI Agents, Web Scraping, Web Crawlers, Claude, Anthropic, Large Language Models (LLMs), Data Scraping, Workflow Automation, Leads, LinkedIn, LinkedIn API, Apollo.io, Business Process Automation, Lead Generation, TypeScript, Node.js, Next.js, React, Tailwind CSS, Shadcn UI, Radix UI, Framer Motion, TanStack Table, Zustand, Recharts, LangGraph, Agentic AI, Agentic Workflow Design, Human-in-the-loop (HITL), Claude API, Artificial Intelligence (AI), AI Model Integration, LLM Integration, AI Integration, Function Calling, Prompt Engineering, Data Pipelines, Data Extraction, Data Integration, Data Engineering, Database Deduplication, B2B Lead Generation, Apify SDK, Third-party APIs, API Integration, REST APIs, Streaming, Server Sent Events (SSE), Prisma, Supabase, PostgreSQL, CSV, CRM, Reporting, Railway, JSON Web Tokens (JWT), Authentication, Playwright, Web Applications, Front-end, Minimum Viable Product (MVP), Solution Architecture, Requirements Analysis, Technical Project Management, Vendor Management, Cost Estimation, Full-stack, Full-stack Development, Claude Code, Agentic Coding, Application Security, Web Security, Continuous Integration (CI), CI/CD Pipelines, IT Deployments, Monorepos, Technical Leadership, AI Project Management, Third-party Integration, AI Architecture, Front-end Development, Software as a Service (SaaS), Back-end Development, Product Management
Back-end Engineer
2024 - 2024
Dream Games
- Built live in-game event services for a top-grossing mobile game with 6+ million active players, using Spring Boot and gRPC over MySQL, Cassandra, Redis, and Elasticsearch.
- Owned features end to end on a 5-engineer back-end team, from the design through production rollout under high-throughput, low-latency constraints.
- Operated event services against live player traffic, tuning data access across the polyglot store for production load rather than test load.
Technologies: Java, Spring Boot, Spring 6, gRPC, MySQL, Cassandra, Redis, Elasticsearch, Amazon Web Services (AWS), Distributed Systems, Microservices, Low-latency Software, SQL Injection Protection, SQL, AWS ECS Fargate, Amazon EC2, AWS Lambda, Amazon S3 (AWS S3), Amazon Elastic Container Service (ECS), Amazon Simple Queue Service (SQS), Amazon Simple Notification Service (SNS), AWS IAM, Amazon CloudWatch, Docker, Linux, Amazon DynamoDB, Databases, Event-driven Architecture, Multi-tenant SaaS, Idempotency, REST APIs, Code Review, Git, JSON Web Tokens (JWT), Algorithms, Data Structures, Programming Languages, Software Engineering, Object-oriented Programming (OOP), Back-end, APIs, API Development, API Design, API Integration, API Documentation, RESTFul APIs, Scalability, Data Architecture, NoSQL, Multitenancy, Enterprise Software, JSON, GitHub, Spring, Amazon RDS, Communication, Reviews, Debugging, API Management, Event-driven Design (EDD), Web Applications, Row-level Security (RLS), Continuous Integration (CI), CI/CD Pipelines, Event-driven Systems, Optimization, Performance, Back-end Development
Software Development Engineer
2022 - 2024
Amazon.com
- Ran a zero-downtime migration of 5+ million Turkish-market user records from a legacy relational store to DynamoDB—(checkout and tax): dual-write, backfill, validation—then a progressive read cutover completed in around 1 hour.
- Delivered cross-team launches as an Away team, including Vendor Powered Coupons on Amazon.com (Netherlands and Sweden).
- Built and operated back-end services in Java/Spring on AWS (DynamoDB, EC2, ECS, Lambda, S3, SQS, SNS, DLQ, IAM) under production checkout traffic.
- Designed for correctness under load, applying idempotency, dead-letter handling, and progressive cutover so a checkout-path change could ship without downtime.
Technologies: Java, Spring 6, Spring Boot, Amazon Web Services (AWS), Amazon DynamoDB, AWS Lambda, AWS ECS Fargate, Amazon EC2, Amazon S3 (AWS S3), Amazon Simple Queue Service (SQS), Amazon Simple Notification Service (SNS), AWS IAM, Database Migration, Idempotency, Distributed Systems, Microservices, Event-driven Architecture, SQL Injection Protection, SQL, Amazon Elastic Container Service (ECS), Amazon CloudWatch, Docker, Terraform, Linux, Redis, Databases, Database Architecture, Multi-tenant SaaS, REST APIs, Code Review, Git, JSON Web Tokens (JWT), Algorithms, Data Structures, Programming Languages, Software Engineering, Object-oriented Programming (OOP), Back-end, APIs, API Development, API Design, API Integration, API Documentation, RESTFul APIs, Scalability, Migration, Data Modeling, Data Architecture, NoSQL, Multitenancy, Enterprise Software, eCommerce, JSON, XML, GitHub, Spring, Amazon RDS, Architecture, Software Architecture, System Architecture, Cloud Architecture, Cloud Infrastructure, System Integration, Integration, Communication, Automation, Integrations, Reviews, Back-end Architecture, Debugging, API Management, Event-driven Design (EDD), Data Pipelines, Data Integration, Data Engineering, Entity Relationships, Database Deduplication, Third-party APIs, Web Applications, Solution Architecture, Row-level Security (RLS), Role-based Access Control (RBAC), Payment APIs, Incident Response, Continuous Integration (CI), CI/CD Pipelines, IT Deployments, Data Migration, Technical Leadership, Third-party Integration, Event-driven Systems, Load Balancers, AWS ALB, AWS Secrets Manager, Release Management, Optimization, Performance, Back-end Development, Product Management
Digital Tech Developer Analyst
2022 - 2022
Accenture
- Built the back end for Roche's customer-experience dashboard in Spring/Java on AWS, delivering the data and API layer behind the client-facing reporting views.
- Worked toward the client's reporting requirements, shipping the API contracts and data access that the dashboard read from.
- Wrote and integrated the SQL data access that fed the dashboard, keeping the API responses aligned with the client's reporting schema.
Technologies: Java, Spring 6, Spring Boot, Amazon Web Services (AWS), Amazon DynamoDB, Amazon S3 (AWS S3), Amazon EC2, REST APIs, SQL, MySQL, Redis, SQL Injection Protection, AWS ECS Fargate, AWS Lambda, Amazon Elastic Container Service (ECS), AWS IAM, Amazon CloudWatch, Docker, Linux, Elasticsearch, Databases, Distributed Systems, Microservices, Event-driven Architecture, Idempotency, Code Review, Git, JSON Web Tokens (JWT), Algorithms, Data Structures, Programming Languages, Software Engineering, Object-oriented Programming (OOP), Back-end, APIs, API Development, API Design, API Integration, API Documentation, RESTFul APIs, Enterprise Software, JSON, GitHub, Spring, Amazon RDS, Communication, CRM, Reviews, Debugging, Event-driven Design (EDD), Data Integration, Reporting, Web Applications, Row-level Security (RLS), Continuous Integration (CI), CI/CD Pipelines, Event-driven Systems, Back-end Development
Junior Software Engineer
2021 - 2022
JotForm
- Joined as a full-stack intern and was kept on part-time as a junior engineer, moving from triaging production issues to owning a feature end to end across the team's product surfaces.
- Led the intern team's back end for a commenting and feedback system on an online PDF editor, designing and shipping the PHP APIs over MySQL from specifications to production.
- Fixed live production bugs across the stack, in both the PHP back end and the React/TypeScript front end, on services used by paying customers.
- Worked inside an established engineering org with code review and a release process, before later moving to build-from-scratch founding work.
Technologies: PHP, MySQL, React, TypeScript, JavaScript, REST APIs, Git, Code Review, SQL Injection Protection, SQL, Docker, Linux, Databases, Algorithms, Data Structures, Programming Languages, Software Engineering, Object-oriented Programming (OOP), Back-end, Full-stack, Full-stack Development, Web Development, APIs, API Development, API Design, API Integration, API Documentation, RESTFul APIs, JSON, XML, GitHub, Communication, Automation, Integrations, Reviews, Back-end Architecture, Debugging, Front-end, API Management, Event-driven Design (EDD), Third-party APIs, Web Applications, Continuous Integration (CI), CI/CD Pipelines, Technical Leadership, Third-party Integration, Event-driven Systems, Front-end Development, Document Parsing, Data Processing, Back-end Development
Webmaster
2020 - 2021
IEEE Bilkent Örenci Kolu
- Built the new IEEE Bilkent Student Branch website on a React front end with a Django back end over SQLite, replacing the previous static site.
- Built the GRC2020 conference site, an HTML5, CSS, and JavaScript front end with a PHP and MySQL signup and login flow that let graduates register and upload their projects.
- Contributed to a Bilkent course-schedule planning tool written in Vue, used by students to lay out their semesters.
- Administered the Debian server hosting ieee.bilkent.edu.tr, handling deployment and uptime for the branch's web presence.
Technologies: React, Django, Python 3, SQLite, Vue 3, PHP, MySQL, HTML, CSS, JavaScript, Debian Linux, Server Administration, SQL Injection Protection, TypeScript, SQL, Node.js, Docker, Linux, Kubernetes, Redis, Databases, REST APIs, Git, JSON Web Tokens (JWT), Algorithms, Data Structures, Programming Languages, Operating Systems, Software Engineering, Object-oriented Programming (OOP), Back-end, Full-stack, Full-stack Development, Web Development, APIs, API Development, API Design, API Integration, API Documentation, RESTFul APIs, JSON, GitHub, Software Architecture, Architecture, Cloud Architecture, Cloud Infrastructure, System Integration, Integration, Minimum Viable Product (MVP), Communication, Python, CRM, Automation, Integrations, Reviews, Security, Back-end Architecture, Debugging, Front-end, API Management, Third-party APIs, Web Applications, Webhooks, Email, NGINX, Transport Layer Security (TLS), Let's Encrypt, Content Management Systems (CMS), Third-party Integration, Document Processing, Front-end Development, Release Management, Performance, System Optimization, Optimization, Document Parsing, Data Processing, Back-end Development
Software Engineer Intern
2020 - 2020
SEN Sistem Entegrasyon
- Built a route-validation system for UAV flight planning that checked planned routes against impact-threat data, flagging unsafe paths before flight.
- Worked on the geospatial layer in Python with GDAL, reading and manipulating geoTIFF terrain and threat files to drive the validation logic.
- Owned the system's API, building it in Flask so the validation could be called as a service rather than run as a one-off script.
Technologies: Python 3, Flask, GDAL, Geospatial Data, GeoTIFF, REST APIs, Databases, Git, Algorithms, Data Structures, Programming Languages, Software Engineering, Object-oriented Programming (OOP), JSON, GitHub, Communication, Python, Reviews, Security, Back-end Development
Web Developer Intern
2019 - 2019
Plum Media Agency
- Built an internal CRM in PHP and jQuery covering the agency's development process, receipts, contacts, and client messaging.
- Built client websites in WordPress across eCommerce, business, and media use cases, handling theme and feature work.
- Built a website cost calculator in jQuery, HTML5, and CSS that gave prospects an estimate before a sales call.
Technologies: WordPress, MySQL, PHP, jQuery, JavaScript, Databases, Database Architecture, HTML, CSS, REST APIs, Git, Algorithms, Data Structures, Programming Languages, Software Engineering, Object-oriented Programming (OOP), Full-stack, Full-stack Development, Web Development, APIs, API Development, API Design, API Integration, API Documentation, RESTFul APIs, JSON, GitHub, System Architecture, Communication, CRM, Automation, Integrations, Reviews, Debugging, Front-end, Web Applications, Content Management Systems (CMS), Front-end Development, Back-end Development, Product Management
Project History
BrandVox AI – Multitenant AI SaaS (RAG, Agents, Real-time Voice)
https://brandvoxai.comBrandVox is an AI customer-engagement platform where the AI is the product, not a feature bolted on.
I built it solo as the dominant author (around 1,557 commits) across 5 production services: an around 90,000-LOC FastAPI back end, a forked Flowise (Node.js/TypeScript) agent engine extended with around 8,700 lines of custom nodes, a React 19 dashboard with a Shadow-DOM embeddable widget, a scraper, and a Next.js SEO site.
The hard part was the retrieval that survives real customer data, not demo corpora. I built hybrid retrieval in the Flowise engine: Qdrant dense vectors fused with BM25 sparse through a custom Reciprocal Rank Fusion ranker, with a weighted 0.7/0.3 ensemble live in production and RRF switchable.
A multi-provider LLM layer (OpenAI, Anthropic, Gemini, Grok) with cascading fallback keeps generation up when a provider fails, and a browser-to-OpenAI Real-time voice agent (PCM16, server VAD) handles barge-in with exactly-once turn persistence. Cost is controlled with provider routing and credit-based per-model accounting per request, on AWS ECS Fargate (Terraform + GitHub Actions). It runs at 1,000+ users and 30+ paying customers, operated solo.
I built it solo as the dominant author (around 1,557 commits) across 5 production services: an around 90,000-LOC FastAPI back end, a forked Flowise (Node.js/TypeScript) agent engine extended with around 8,700 lines of custom nodes, a React 19 dashboard with a Shadow-DOM embeddable widget, a scraper, and a Next.js SEO site.
The hard part was the retrieval that survives real customer data, not demo corpora. I built hybrid retrieval in the Flowise engine: Qdrant dense vectors fused with BM25 sparse through a custom Reciprocal Rank Fusion ranker, with a weighted 0.7/0.3 ensemble live in production and RRF switchable.
A multi-provider LLM layer (OpenAI, Anthropic, Gemini, Grok) with cascading fallback keeps generation up when a provider fails, and a browser-to-OpenAI Real-time voice agent (PCM16, server VAD) handles barge-in with exactly-once turn persistence. Cost is controlled with provider routing and credit-based per-model accounting per request, on AWS ECS Fargate (Terraform + GitHub Actions). It runs at 1,000+ users and 30+ paying customers, operated solo.
Kodwai – AI-fluency Assessment & AI-native Interview Platform
https://kodwai.comKodwai measures how well an engineer directs AI coding agents rather than raw coding.
I built the full stack solo: a published TypeScript CLI (@kodwai/cli), a FastAPI scoring back end on Turso/libSQL, and Next.js 16 clients for a B2C developer leaderboard and a B2B interview product that shares infrastructure.
Scoring runs in 2 phases. Phase 1 is deterministic: test pass rate, lint and nesting-depth heuristics, and iteration signals, with skipped-signal renormalization so a submission without an API key still gets a meaningful objective score. Phase 2 is an anchored 0-10 Claude Sonnet judge over spec precision, verification rigor, and decomposition, median-of-N sampled for stability.
The piece clients ask about most is the proxy: an async Anthropic proxy that swaps a per-session token for a server-held key, parses streaming SSE deltas to compute true per-token USD cost in real time, and enforces per-session time and budget limits (HTTP 402 at the cap), so a real key never touches an untrusted candidate machine and interviewer spend stays bounded. Stored 3rd-party keys use AES-256-GCM with a fresh nonce per write.
I built the full stack solo: a published TypeScript CLI (@kodwai/cli), a FastAPI scoring back end on Turso/libSQL, and Next.js 16 clients for a B2C developer leaderboard and a B2B interview product that shares infrastructure.
Scoring runs in 2 phases. Phase 1 is deterministic: test pass rate, lint and nesting-depth heuristics, and iteration signals, with skipped-signal renormalization so a submission without an API key still gets a meaningful objective score. Phase 2 is an anchored 0-10 Claude Sonnet judge over spec precision, verification rigor, and decomposition, median-of-N sampled for stability.
The piece clients ask about most is the proxy: an async Anthropic proxy that swaps a per-session token for a server-held key, parses streaming SSE deltas to compute true per-token USD cost in real time, and enforces per-session time and budget limits (HTTP 402 at the cap), so a real key never touches an untrusted candidate machine and interviewer spend stays bounded. Stored 3rd-party keys use AES-256-GCM with a fresh nonce per write.
Ksenda – Multitenant BYOK Cold-email SaaS
https://ksenda.comKsenda is a bring-your-own-key cold email platform where each tenant supplies their own Apollo, Gemini, and SMTP credentials.
I built Ksenda on Next.js 16, React 19, and Prisma 7 over Turso (libSQL) with 14 data models and row-level isolation across a 73-route API. The AI work is a batched, concurrent, per-domain-cached Gemini classifier (urlContext plus Google Search grounding) that gates lead imports on a company's AI presence at roughly $0.0018 per company, with self-healing retries for verdicts the model drops on large batches.
Follow-ups are RFC822-correct: Ksenda captures the initial Message-Id and replays it as In-Reply-To and References with a forced Re: subject, so Day 3/7/14 sequences collapse into the original Gmail thread. The automation runs as an Inngest pipeline that decomposes each per-row import, send, and follow-up into its own step (retries:0 to prevent double-sends, per-tenant concurrency 1) so multi-minute runs never hit serverless step timeouts, with daily caps and a timezone-aware send window. It runs at around 15% reply rate across 5,000+ emails (observed operating metric; reply detection is manual today).
I built Ksenda on Next.js 16, React 19, and Prisma 7 over Turso (libSQL) with 14 data models and row-level isolation across a 73-route API. The AI work is a batched, concurrent, per-domain-cached Gemini classifier (urlContext plus Google Search grounding) that gates lead imports on a company's AI presence at roughly $0.0018 per company, with self-healing retries for verdicts the model drops on large batches.
Follow-ups are RFC822-correct: Ksenda captures the initial Message-Id and replays it as In-Reply-To and References with a forced Re: subject, so Day 3/7/14 sequences collapse into the original Gmail thread. The automation runs as an Inngest pipeline that decomposes each per-row import, send, and follow-up into its own step (retries:0 to prevent double-sends, per-tenant concurrency 1) so multi-minute runs never hit serverless step timeouts, with daily caps and a timezone-aware send window. It runs at around 15% reply rate across 5,000+ emails (observed operating metric; reply detection is manual today).
Pitch IQ - Agentic live-sports companion
https://github.com/egehakan/pitch-iqPitch IQ is an AI companion for a live football tournament that I built to push LangGraph as far as one product can.
A single supervisor graph implements all seven canonical agent runtime patterns end to end: a structured-output intent router; a ReAct agent bound to eight live-data tools whose prompt forbids stating any unverified fact; parallel provider fan-out; an orchestrator-worker briefing writer over the Send map-reduce API; a generator-critic prediction loop that checks the model's win probabilities against a de-vigged market line and revises up to two rounds; two-tier memory over a Postgres checkpointer and store; and a human-in-the-loop interrupt that pauses to confirm before it locks a bracket.
The chat streams the agent's working to the UI, the routed specialist, each tool call with live status, then tokens, over a custom NDJSON protocol.
Behind it sits an async FastAPI back end, a two-schema Postgres, Alembic, APScheduler, and a provider layer with caching, rate-limiting, and failover pulling real live data.
A single supervisor graph implements all seven canonical agent runtime patterns end to end: a structured-output intent router; a ReAct agent bound to eight live-data tools whose prompt forbids stating any unverified fact; parallel provider fan-out; an orchestrator-worker briefing writer over the Send map-reduce API; a generator-critic prediction loop that checks the model's win probabilities against a de-vigged market line and revises up to two rounds; two-tier memory over a Postgres checkpointer and store; and a human-in-the-loop interrupt that pauses to confirm before it locks a bracket.
The chat streams the agent's working to the UI, the routed specialist, each tool call with live status, then tokens, over a custom NDJSON protocol.
Behind it sits an async FastAPI back end, a two-schema Postgres, Alembic, APScheduler, and a provider layer with caching, rate-limiting, and failover pulling real live data.
Education
2017 - 2022
Bachelor of Science Degree in Computer Science
Bilkent University - Ankara, Turkey
Certifications
APRIL 2021 - PRESENT
Data Engineering Bootcamp
Trendyol
Skills
Libraries/APIs
OpenAI API, Claude API, REST APIs, API Development, Pydantic, LinkedIn API, Node.js, React, Turso libSQL, Stripe, Stripe Connect, SQLAlchemy, APScheduler, Playwright, Facebook SDK, Facebook API, Framer Motion, TanStack Table, Recharts, Zod, Vue 3, GDAL, jQuery, Terragrunt
Tools
Claude Code, Okapi BM25, Git, ChatGPT, Claude, GitHub, Amazon Elastic Container Service (ECS), Terraform, Amazon CloudWatch, Amazon Simple Queue Service (SQS), Amazon Simple Notification Service (SNS), AWS IAM, Claude Agent SDK, Shell, Shadcn UI, Pytest, NGINX, Let's Encrypt, Vitest, Drizzle ORM, Amazon Elastic Container Registry (ECR), BigQuery, Sentry, Grafana, Google Analytics, Prisma
Languages
Python 3, TypeScript, Python, Java, SQL, JavaScript, HTML, CSS, Bash, Scala, PHP, Go, XML
Frameworks
Next.js, Spring Boot, Spring 6, LangGraph, Django, Flask, JSON Web Tokens (JWT), Express.js, Tailwind CSS, Spring, Alembic, Apache Spark, gRPC, LlamaIndex
Paradigms
Object-oriented Programming (OOP), Model Context Protocol (MCP), Microservices, Automation, Back-end Architecture, Event-driven Design (EDD), Continuous Integration (CI), Event-driven Architecture, B2C, Role-based Access Control (RBAC), DevOps, Requirements Analysis
Platforms
Amazon EC2, Amazon Web Services (AWS), Docker, PostHog, AWS Lambda, Linux, Vercel, LangSmith, AWS ALB, Apache Kafka, Apache Flink, Debian Linux, WordPress, Kubernetes
Storage
PostgreSQL, Databases, Amazon DynamoDB, Redis, Amazon S3 (AWS S3), NoSQL, JSON, Data Pipelines, MySQL, SQLite, Turso, SQL Injection Protection, Data Integration, Elasticsearch, Cassandra, Database Migration, Database Architecture, MongoDB
Other
FastAPI, LangChain, RAG Systems, Algorithms, Data Structures, Programming Languages, Artificial Intelligence (AI), Software Engineering, Retrieval-augmented Generation (RAG), Hybrid Search, Qdrant, Vector Databases, Vector Search, Reciprocal Rank Fusion, Gemini API, AI Agent Orchestration, AI Agents, Agentic Workflow Design, Tool Calling, Prompt Engineering, Server Sent Events (SSE), Flowise, AWS ECS Fargate, Multimodel AI, Model Agnostic Development, Agent Orchestration, LLM Orchestration, Pgvector, Keyword Searches, LLM-as-Judge, Evaluation, LLM Evals, Per-token Cost Metering, AI Engineering, Multimodal GenAI, Multimodal Models, Embedding Models, Semantic Search, Chunking, Generative Artificial Intelligence (GenAI), Human-in-the-loop (HITL), Large Language Models (LLMs), Agentic AI, Agentic AI Systems, Conversational AI, AI Chatbots, AI Integration, LLM Integration, OpenAI, Anthropic, Gemini, Back-end, Full-stack, Full-stack Development, Web Development, APIs, API Design, API Integration, API Documentation, RESTFul APIs, Authentication, Multitenancy, Software Architecture, System Architecture, Agentic RAG Systems, Agentic Coding, Communication, Structured Outputs, Generator-Evaluator, Streaming, Web Crawlers, Web Scraping, Data Scraping, Leads, LinkedIn, Lead Generation, Multi-agent Orchestration, Workflow, Workflows, Multi-agent Systems, Integrations, Reviews, Workflow Automation & System Integration, LLM Agents, API Management, Business Process Automation, AI Model Integration, Data Extraction, Entity Relationships, B2B Lead Generation, Third-party APIs, Railway, Web Applications, Solution Architecture, Row-level Security (RLS), OAuth, Email, CI/CD Pipelines, Technical Leadership, AI Project Management, Third-party Integration, Durable Execution Workflows, AI Architecture, Chatbots, Event-driven Systems, Software as a Service (SaaS), Document Parsing, Data Processing, Back-end Development, Computer Organization, Machine Learning, OpenAI Realtime API, WebSockets, Server VAD, Fal.ai, Multi-tenant SaaS, Cloudflare, Distributed Systems, Low-latency Software, Idempotency, Code Review, Realtime Voice AI, RFC82, Apollo.io, Re-ranking, Amazon Bedrock AgentCore, Image Generation, Video Generation, Natural Language Processing (NLP), Function Calling, Generative Pre-trained Transformers (GPT), Large Language Model Operations (LLMOps), AI Automation, Supabase, Real-time Data, Scalability, Migration, Data Modeling, Data Architecture, Enterprise Software, eCommerce, Amazon RDS, Command-line Interface (CLI), Architecture, Cloud Architecture, Cloud Infrastructure, System Integration, Integration, AI Tools, AI Product Strategy, Workflow Automation, Minimum Viable Product (MVP), User Experience (UX), User Interface (UI), Single Sign-on (SSO), Async.js, Facebook, CRM, Security, Debugging, Front-end, Radix UI, Zustand, Data Engineering, Database Deduplication, Apify SDK, CSV, Reporting, Technical Project Management, Vendor Management, Cost Estimation, Supabase Auth, Server-side PDF Generation, Legal Technology (Legaltech), Payment APIs, Webhooks, Resend, Application Security, Web Security, Security Audits, Incident Response, Privacy, Transport Layer Security (TLS), IT Deployments, Turborepo, Monorepos, Data Migration, Content Management Systems (CMS), Server-side Rendering (SSR), Bun, Hono, oRPC, Full-text Search, DevKit, Cohere, Document Processing, Front-end Development, OpenTelemetry, Load Balancers, AWS Secrets Manager, Release Management, Linear, Performance, Optimization, System Optimization, Gmail, Product Management, Operating Systems, GitHub Actions, Server Administration, Geospatial Data, GeoTIFF, Google Search Console, Inngest, Nodemailer, SMTP, Pinecone, Weaviate, Hugging Face, Machine Learning Operations (MLOps), Design, Accessibility
Collaboration That Works
How to Work with Toptal
Toptal matches you directly with global industry experts from our network in hours—not weeks or months.
1
Share your needs
Discuss your requirements and refine your scope in a call with a Toptal domain expert.
2
Choose your talent
Get a short list of expertly matched talent within 24 hours to review, interview, and choose from.
3
Start your risk-free talent trial
Work with your chosen talent on a trial basis for up to two weeks. Pay only if you decide to hire them.
Top talent is in high demand.
Start hiring