
Alex Baas
Verified Expert in Engineering
Full-stack Developer
Berlin, Germany
Toptal member since April 15, 2021
Alex is a principal AI engineer with 15 years of experience designing, building, and deploying production agentic AI end to end: LLM agents, multi-agent orchestration, RAG/GraphRAG, and MCP tools, shipped behind LLM evals, guardrails, and AI governance for regulated health and life sciences. He brings ML and data engineering roots, full delivery on AWS and GCP (Docker, Kubernetes, and Terraform), and an INSEAD MBA.
Portfolio
Experience
- Python - 10 years
- Machine Learning - 8 years
- AI Engineering - 8 years
- Large Language Models (LLMs) - 4 years
- Retrieval-augmented Generation (RAG) - 3 years
- Agentic AI - 3 years
- AI Security - 2 years
- Model Context Protocol (MCP) - 2 years
Work Experience
Principal AI Engineer
Elysium Health
- Grew the engagement from full-stack Ruby on Rails development into leading AI engineering for a health and longevity company handling regulated consumer-health and genetic data.
- Led design and prototyping of an agentic DNA-insights assistant over customers' DNA test results: multi-agent orchestration with tool calling (MCP), personalized genomic insights, and interactive visualization.
- Built GraphRAG over a knowledge graph of genomics research (PubMed papers to genes, variants, nutrients, outcomes): hybrid vector and graph retrieval, reranking, and source citations grounding every answer.
- Built a recommendation agent matching DNA results to best-suited supplement formulations, powering personalization and the sales funnel.
- Engineered LLM guardrails for regulated health content: health-claim compliance (FDA/FTC structure-function rules, EU health-claims regulation), medical-advice refusal, prompt-injection defense, and output verification.
- Implemented privacy-by-design for genetic data (GDPR special category, HIPAA-aligned): PII/PHI redaction before LLM calls, consent-scoped retrieval, and audit trails for AI governance.
- Set up LLM evaluation and observability as release gates: golden datasets, LLM-as-a-judge grounding and faithfulness scoring, and end-to-end tracing.
- Owned end-to-end delivery: designed, built, and deployed AI services on AWS and GCP with Docker, Kubernetes, Terraform, Ansible, and CI/CD.
- Built the ML-ready data foundation (BigQuery, dbt) and designed churn-prediction models (XGBoost, LightGBM) feeding personalization.
Staff AI Platform Engineer
Scilife
- Designed and built agentic AI into a GxP-regulated eQMS SaaS for life sciences (quality management for pharma, biotech, and medical-device companies) in a fixed-scope engagement.
- Led engineering of the LLM platform service (Python, FastAPI, AWS Bedrock/Claude): REST APIs mirrored as MCP tools, OpenTelemetry LLM observability, and per-call token and cost budgets.
- Implemented signed, versioned prompt bundles with provenance recorded on every LLM response, giving the regulated product an audit trail for AI output.
- Designed the product's agentic AI chat: one agent with a growing set of skills over QMS data (events, CAPA, change control, training, documents) and permission-aware, cited answers.
- Built the first release of the agentic chat feature, human-in-the-loop by design (advises, never acts) with a full audit trail of every question and answer.
- Built eval-driven release gates in CI/CD: SME golden datasets, rubric-based LLM-as-a-judge juries calibrated against human reviewers, and per-metric floors.
- Shipped grounded document-AI extraction and generative assessment features behind the eval gates.
- Architected the end-to-end RAG and agent stack: document ingestion (parsing, OCR, chunking, embeddings), context engineering, governed tool calling, and output verification; designed permission-aware hybrid RAG with citations.
- Conducted LLM security red teaming (OWASP LLM Top 10, STRIDE; Promptfoo, Garak, and PyRIT) and designed the mitigations and guardrails.
- Designed the AI quality and governance framework: evals, observability, and compliance evidence mapped to the EU AI Act, ISO/IEC 42001, GAMP 5, and FDA 21 CFR Part 11.
Senior AI/ML Engineer (RAG)
RegBot
- Developed and deployed a retrieval-augmented generation (RAG) application for a GovTech regulatory AI product, using GPT-4 with TensorFlow and PyTorch to improve retrieval quality.
- Built ML models in Julia and Python and integrated them into the RAG pipeline, increasing prediction accuracy by 20% on retrieval tasks.
- Orchestrated the LLM workflows with LangChain and LangGraph, traced with LangSmith, on a serverless AWS stack with Amazon Cognito authentication.
- Engineered high-performance data workflows in Julia, cutting data processing time by 25%, and scaled the infrastructure to 99.9% uptime for AI-driven government services.
LLM & Data Engineer (Legal Tech)
Redgrave Strategic Data Solutions, LLC
- Executed an MLOps strategy for NLP that automated legal-document analysis, boosting model accuracy by 20% and improving investigation outcomes.
- Devised data engineering and monitoring solutions for complex legal analytics, reducing error rates by 25% and optimizing data workflows.
- Pioneered a low-code Retool integration over the company's APIs, improving operational efficiency by 30% and accelerating app delivery for a 27-person legal-tech startup.
AI Platform Architect (BI SaaS)
Polymer Search, Inc.
- Led the incorporation of AI and ML capabilities (LLMs, OpenAI) into the core BI product, driving a 45% improvement in customer engagement and personalization.
- Defined and executed the technology roadmap and cloud-native platform architecture, increasing system reliability by 35%.
- Designed a Google Analytics 4 data-management strategy that improved data accuracy by 30% and strengthened data-driven decision-making across the company.
- Integrated complex third-party APIs, including Salesforce, cutting data retrieval time by 40% and enabling real-time reporting and business insight.
Senior Data Engineer (Analytics & BI)
iptiQ Life S.A. UK Branch
- Designed and implemented the monitoring and analytics layer, with 20+ Grafana dashboards for business and IT analytics at an enterprise insurtech.
- Created a CI/CD pipeline serving 50+ microservices inside one monorepo, with automated code-quality gates in SonarQube.
- Migrated 50+ independent GitLab repositories into a single monorepo, unifying builds, ownership, and delivery.
Principal Machine Learning Engineer
Storyroom
- Led ML engineering for campaign intelligence at an AI-driven marketing platform: predictive models (PyTorch and scikit-learn) for audience targeting and campaign forecasting in production.
- Prototyped generative AI for marketing content on GPT-3 and early ChatGPT APIs (2022), building prompt-engineering and LLM content workflows.
- Architected the PostgreSQL data layer and pipelines feeding model training and analytics, and refactored Python and Go services for a 50% server performance gain.
- Introduced integration testing across the ML and data services to improve code quality and release confidence.
Staff Machine Learning Engineer
CoachHub
- Built NLP-powered coach matching and content recommendation (TensorFlow) for a global talent-development platform used by millions of users.
- Productionized ML features in Python and Node.js microservices on AWS and GCP with Docker, Kubernetes, and CI/CD.
- Architected the REST and GraphQL APIs connecting ML services to the product.
- Introduced test-driven development and helped build the CI/CD pipeline, speeding up the product release cycle.
Senior Software Engineer, Machine Learning
Doctolib
- Developed NLP models (TensorFlow and PyTorch) for patient-doctor message classification and routing on sensitive health data under GDPR.
- Enabled end-to-end encryption for 10,000,000 medical documents on Europe's leading healthcare booking and telehealth platform.
- Built end-to-end product features for healthcare operations across Ruby on Rails, Go, and React, including adapting the interface for the Italian market launch.
- Initiated and led a refactoring program that reduced critical bugs by 20%.
Lead Software Engineer
Dropbyke
- Built a cross-functional engineering team and set up the engineering culture and agile process for an electric-scooter-sharing startup.
- Developed the cross-platform rider app (React, PWA) and its PostgreSQL back end.
- Scaled the product from 0 to 10,000 users across five countries.
ERP Software Engineer & Team Lead
Eastbridge
- Designed and implemented a quick-response management accounting system on an ERP platform (SAP), reducing the company's required working capital by 50%.
- Created a resource-planning system that cut energy consumption by 40% by moving heating from fossil to renewable energy sources.
- Launched an online tender system that reduced purchase prices by 20%, and built and led a team of five engineers using agile.
Project History
Portfolio
https://alexbaas.com/Education
Master of Business Administration (MBA) in Business Administration
INSEAD - Singapore, Singapore
Master's Degree in Computer Science
University of the People - Pasadena, CA, USA
Certifications
AWS Certified Machine Learning – Specialty
Amazon Web Services (AWS)
AWS Certified DevOps Engineer – Professional
Amazon Web Services (AWS)
AWS Certified Solutions Architect – Professional
Amazon Web Services (AWS)
Professional Scrum Master
Scrum.org
Certified International Investment Analyst (CIIA)
https://www.aciia.org
Skills
Libraries/APIs
React, Node.js, React Redux, REST APIs, Vue, OpenAPI, jQuery, GitHub API, ActiveRecord, Context API, Stripe API, Stripe Connect, Braintree API, Twilio API, Lit, AWS Amplify, Auth0 API, Auth0 Management API v2, Google Analytics API, Stripe, Pandas, D3.js, HTTP API, LocalStorage, Typeform, Typeform.io, Garmin API, Fitbit API, Liquid, SciPy, OpenAI API, TensorFlow, PyTorch, XGBoost, Hugging Face Transformers, Claude API, Pydantic, API Development, Salesforce API, Scikit-learn
Tools
Slack, Jira, Vim Text Editor, GitHub, CircleCI, Figma, Git, Prisma, Postman, Sequelize, Docker Compose, Webpack, Create React App, Lighthouse, RSpec, Expo, GitLab, Atlassian, Auth0, SonarQube, BigQuery, GitLab CI/CD, Grafana, Kibana, Apache Airflow, Amazon Athena, AWS Glue, Superset, Google Analytics, Amazon CloudWatch, Terraform, Microsoft Excel, RabbitMQ, Amazon CloudFront CDN, Microsoft Access, Amazon Cognito, Beanstalk, Docker Hub, Babel, AWS CloudFormation, AWS IAM, Amazon Elastic MapReduce (EMR), AWS Command Line Interface (CLI), AWS ELB, Amazon Simple Email Service (SES), AWS SDK, ChatGPT, Looker, Claude, GraphRAG, Claude Code, Claude Agent SDK, Amazon SageMaker, AI Prompts, AWS Step Functions, Ansible, Retool
Languages
JavaScript, TypeScript, SQL, Ruby, CSS, HTML, GraphQL, HTML5, Sass, ECMAScript (ES6), Python, Bash, Bash Script, Snowflake, Go, CSS3, YAML, Julia
Frameworks
Ruby on Rails (RoR), Tailwind CSS, Vanilla JS, Jest, Express.js, Cypress, Next.js, Redux, Material UI, Swagger, NestJS, minitest, JSON Web Tokens (JWT), React Native, Svelte, Django, Spark, Presto, Selenium, Bootstrap, Flask, Nuxt.js, Flux, LangGraph, Streamlit, AI Risk Management Framework, LlamaIndex, Agentic Frameworks
Paradigms
Change Management, Agile Software Development, Test-driven Development (TDD), Testing, Refactoring, Unit Testing, Agile, REST, Microservices, Microservices Architecture, Serverless Architecture, Object-oriented Programming (OOP), Database-driven Web App Development, UI Design, UX Design, Scrum, ETL, Responsive Layout, DevOps, Test Automation, Automated Testing, Business Intelligence (BI), Database Design, Web Performance Optimization (WPO), Search Engine Optimization (SEO), Responsive Web Design (RWD), Automation, Continuous Integration (CI), Management, Model View ViewModel (MVVM), ETL Implementation & Design, Web Architecture, Data-oriented Design, API Architecture, Best Practices, Low-code Development, RESTful Development, B2B, Model Context Protocol (MCP), HIPAA Compliance
Platforms
Linux, Firebase, Heroku, MacOS, Amazon Web Services (AWS), Google Cloud Platform (GCP), Contentful, Docker, Azure, Ubuntu, AWS Elastic Beanstalk, Amazon EC2, AWS Lambda, Kubernetes, Twilio, Mobile, Netlify, DigitalOcean, Amazon, AWS Security Token Service (STS), Windows, Microsoft, Mapbox, LangSmith, Langfuse, Harness, WordPress, AWS IoT, Fabric Lakehouse, Microsoft Fabric
Storage
PostgreSQL, NoSQL, Amazon DynamoDB, Cloud Firestore, JSON, Database Modeling, RDBMS, Relational Databases, Redis, Amazon S3 (AWS S3), Google Cloud, MySQL, MongoDB, Data Pipelines, Elasticsearch, SQLite, Data Integration, Database Architecture, Redis Cache, Redshift, Databases, Oracle Cloud, Database Administration (DBA), Neo4j, DB
Industry Expertise
Web Design, Project Management, Cybersecurity
Other
Software Project Management, Entrepreneurship, Progressive Web Applications (PWAs), Styled-components, SAP ERP, Website Performance, Dependency Management, GitHub Actions, Front-end, User Interface (UI), Web Development, Prototyping, Ajax, Architecture, Integration Testing, QA Testing, Pipelines, CI/CD Pipelines, Cloud, Startups, APIs, Full-stack, Back-end, RESTful Microservices, API Integration, Software Architecture, API Gateways, Data Modeling, TypeORM, Serverless, Solution Architecture, Amazon RDS, Data Engineering, Data Migration, Data, Algorithms, Lambda Functions, Storybook, Monorepos, Localization, Web Security, Chrome Extensions, Encryption, Data Encryption, End-to-end Implementation (E2E), Web App Development, PWA, Payment APIs, BrainTree, Startup Consulting, MVP Design, Full-stack Development, Design, User Experience (UX), Performance, Bots, Documentation, Git Flow, Front-end Development, Web Components, Single-page Applications (SPAs), Responsive Web Apps, Minimum Viable Product (MVP), Customer Relationship Management (CRM), Healthcare IT, Healthcare Management Systems, Single Sign-on (SSO), ETL Tools, Prometheus, Data Analysis, Data Visualization, Hospitality, Revenue Management, Apache Superset, Metabase, SEO Tools, Google BigQuery, Natural Language Processing (NLP), Google Cloud Natural Language, Quality Assurance (QA), Automated UI Testing, Test Automation Frameworks, QA Automation, Data Analytics, Dashboards, Monitoring, Gatsby, ESLint, Booking Apps, Booking Systems, Early-stage Startups, Appointment Booking, Finance, Fintech, Data Warehousing, Data Architecture, Data Science, Financial Modeling, Investment Analysis, Business Analysis, A/B Testing, Learning Management Systems (LMS), Feasibility, Feasibility Studies, Financial Planning & Analysis (FP&A), Reporting, WebSockets, Google SEO, Front-end Architecture, MERN Stack, Scalable Architecture, Technical Leadership, Software Design, DOM, eCommerce, Security, IT Security, Cloud Architecture, Web Scraping, Networking, Leadership, Computer Vision, Chatbots, Team Leadership, AWS DevOps, Cloud Infrastructure, HTTP, Big Data, DevOps Engineer, Apollo, Scalability, Cryptography, Zoho, API Testing, SaaS, Scraping, Big Data Architecture, CRM APIs, Infrastructure as Code (IaC), AWS Cloud Architecture, Responsive UI, Authentication, Site Reliability Engineering (SRE), Web UI, Business Services, Third-party APIs, Back-end Development, Data Build Tool (dbt), Caching, Online Payments, Inventory Management, Infrastructure, API Design, Amazon API Gateway, Shell Scripting, Statistical Analysis, Webhooks, Reverse Engineering, Marketplaces, Data Extraction, Performance Tuning, Headless Software, Infrastructure Monitoring, System Architecture, SDKs, Data Protection, Data Scraping, Data Structures, Cloud Services, ELT, ETL Development, Responsive Design, Apollo Server, OpenAI, Integration, RESTful Services, RESTful Web Services, System Design, Projects, Engineering, Artificial Intelligence (AI), Large Language Models (LLMs), Language Models, Web Applications, Data-driven Decision-making, Generative Pre-trained Transformers (GPT), Google, Networks, Offshore Team Management, Discord Bots, Mapping, Charts, Lead Generation, CRM Systems, Process Flows, Excel 365, Microsoft Forms, Data Management, Database Schema Design, Code Review, Estimations, NMI Payment Gateway, FinOps, Accessibility, Accessible Rich Internet Applications (ARIA), CSV File Processing, IT Business Analysis, Business Analytics, Embedded Business Intelligence, Machine Learning Operations (MLOps), Generative Artificial Intelligence (GenAI), Light LLMs, Open-source LLMs, Multistage LLM Chains, LangChain, Fivetran, SvelteKit, Supabase, Retrieval-augmented Generation (RAG), OpenAI GPT-4 API, OpenAI SDK, Pinecone, Agentic AI, RAG Architecture, Large Language Model Operations (LLMOps), Multimodal GenAI, AI Agents, ReAct Agents, Large Model Systems Organization (LMSYS), Quantization, Model Evaluation, Hugging Face, NeoVim Text Editor, Embedding Models, AI Evaluation, AI Security, AI Governance, FastAPI, Amazon Bedrock, Knowledge Graphs, Machine Learning, Prompt Engineering, AI Engineering, AI Agent Orchestration, Multi-agent Systems, LLM Agents, Agentic RAG Systems, Agentic Workflow Design, Function Calling, Human-in-the-loop (HITL), Context Engineering, LLM Integration, Anthropic, Vector Databases, Pgvector, Semantic Search, AI Architecture, Red Teaming, Threat Modeling, OWASP Top 10, Responsible AI, AI Compliance, AI Risk Assessment, GxP Compliance, Regulatory Compliance, Deep Learning, MLflow, RAG Systems, AI Consulting, AI Integration, AI Tools, AI Workflow, Integrations, ChatGPT API, Agentic AI Systems, AI Safety, AI-assisted Development, ChatGPT Prompts, AI Systems, Agentic Coding, AI Modeling, Software Engineering, Microsoft Azure, Streaming, Statistics, Multi-tenant Architecture, Multi-tenant SaaS, Multitenancy, Software as a Service (SaaS), HIPAA, Business Strategy, Product Strategy, AI Product Strategy, AI Product Management, Orchestration, Enterprise Architecture, Workday, Observability, AI Red Team, OpenTelemetry, Google Analytics 4 (GA4), Recommendation Systems, GDPR
How to Work with Toptal
Toptal matches you directly with global industry experts from our network in hours—not weeks or months.
Share your needs
Choose your talent
Start your risk-free talent trial
Top talent is in high demand.
Start hiring