Ahmet is available for hire
Hire AhmetAhmet Yasin Aytar
Verified Expert in Engineering
Python Developer
Istanbul, Turkey
Toptal member since March 6, 2026
Bio
Ahmet is an AI engineer with 5+ years of experience building production-grade LLM systems, agentic frameworks, and RAG pipelines for regulated industries. His work spans conversational banking agents, intelligent search systems, and local LLM infrastructure, all deployed at scale. He holds a master's degree in data science, is currently pursuing a PhD in AI, and has published peer-reviewed research on RAG architectures in Elsevier.
Portfolio
Architecht
Python, SQL, Artificial Intelligence (AI), AI Agents, Data Science...
Finiti Legal
Python, LangGraph, Pinecone, Azure, Large Language Models (LLMs), Git, GitHub...
Sabanci University
Python, PyTorch, TensorFlow, Scikit-learn, Large Language Models (LLMs)...
Experience
- Python - 6 years
- Machine Learning - 6 years
- Artificial Intelligence (AI) - 6 years
- Data Science - 6 years
- SQL - 6 years
- LangGraph - 4 years
- Retrieval-augmented Generation (RAG) - 3 years
- Large Language Models (LLMs) - 3 years
Preferred Environment
Python, Retrieval-augmented Generation (RAG), Large Language Models (LLMs), Machine Learning Operations (MLOps), AI Agents, SQL, Jupyter Notebook
The most amazing...
...thing I've built is a multi-layer intelligent search system deployed in production and serving over 6,000 customers daily.
Work Experience
Senior AI Engineer
2022 - PRESENT
Architecht
- Built an MCP server from scratch using FastMCP and Python as the deployment layer for the banking agent framework's tools, handling all configuration and optimization. Now used by 50+ developers company-wide.
- Developed a conversational banking agent framework using LangGraph, LangChain, and FastAPI for Kuwait Finance House, enabling customers to complete 10+ operation types without screen-based navigation.
- Implemented a multi-layer intelligent search algorithm combining exact matching, fuzzy typo handling, and semantic embedding retrieval using Milvus, serving over 6,000 daily users in production.
- Built machine learning (ML) models using Scikit-learn to predict customer product preferences during digital onboarding for the bank, improving personalization accuracy and increasing cross-sell conversion rates.
- Applied non-parametric ML models to predict potential customer lifetime value, increasing segmentation accuracy by 20% and enabling more effective targeted marketing campaigns across retail banking.
- Led development of an in-house MLOps platform using Apache Airflow, MLflow, and Docker, reducing ML model time-to-production by 40% across five concurrent banking projects.
- Led R&D on synthetic data generation using GAN architectures for imbalanced credit datasets, built an evaluation framework, and published the results as an academic book chapter at an academic conference.
- Designed and deployed a scalable local LLM serving infrastructure using vLLM and Ollama on Kubernetes with dual GPU nodes, building RESTful APIs to enable secure company-wide access to large language models.
Technologies: Python, SQL, Artificial Intelligence (AI), AI Agents, Data Science, Azure DevOps Services, Linux, Git, Docker, Machine Learning, Scikit-learn, PyTorch, LangChain, LangGraph, FastAPI, Milvus, AWS IoT, Apache Airflow, vLLM, Ollama, MLflow, REST, Retrieval-augmented Generation (RAG), Machine Learning Operations (MLOps), Jupyter Notebook, Pandas, NumPy, Natural Language Processing (NLP), Semantic Search, Agentic AI, AI Architecture, Large Language Model Operations (LLMOps), Graphics Processing Unit (GPU), AI Model Training, Amazon Web Services (AWS), Generative Artificial Intelligence (GenAI), RAG Systems, Prompt Engineering, OpenAI, Anthropic, Vector Databases, Hyperparameter Tuning, API Integration, Microsoft Copilot Studio, AI Agent Orchestration, AI Integration, APIs, Software Architecture, Architecture, Data Analytics, Data Analysis, ETL, Forecasting, Agentic AI Systems, Agentic Frameworks, Imbalanced-learn, LightGBM, Model Evaluation, XGBoost, Cloud Platforms, A/B Testing, RAG Pipelines, Recommendation Systems, Embedding Models, Data Pipelines, Data Modeling, Elasticsearch, Microservices, Model Context Protocol (MCP), Claude Code, Hugging Face Transformers, RAG Architecture, Technical Writing, Artificial Intelligence as a Service (AIaaS), Claude, Gemini, AI Chatbots, Chatbots, Automation, Microsoft Copilot, Technology, Azure OpenAI Service
Senior AI Engineer
2025 - 2026
Finiti Legal
- Engineered secure, multi-tenant data ingestion pipelines for Finiti, a US legal-tech startup, using Python, Azure, Redis, and Pinecone with SOC 2 compliance, automating corporate law document processing.
- Built advanced RAG-based search agents using LangGraph and Pinecone that auto-generate regulatory content for corporate lawyers, transforming manual legal research into intelligent, agentic workflows across secure multi-tenant Azure infrastructure.
- Designed and executed RAG evaluation benchmarks measuring retrieval accuracy, latency, and relevance across search agents, iterating on chunking strategies, reranking algorithms, and embedding models to optimize legal document search performance.
Technologies: Python, LangGraph, Pinecone, Azure, Large Language Models (LLMs), Git, GitHub, AI Agents, Redis, Retrieval-augmented Generation (RAG), Artificial Intelligence (AI), Azure DevOps Services, Docker, Machine Learning, LangChain, Pandas, NumPy, REST, Natural Language Processing (NLP), FastAPI, Semantic Search, Agentic AI, AI Architecture, Large Language Model Operations (LLMOps), Amazon Web Services (AWS), Generative Artificial Intelligence (GenAI), RAG Systems, OpenAI, Anthropic, Vector Databases, Hyperparameter Tuning, API Integration, Microsoft Copilot Studio, AI Agent Orchestration, AI Integration, APIs, Software Architecture, Architecture, Data Analytics, Data Analysis, ETL, Forecasting, Agentic AI Systems, Agentic Frameworks, Imbalanced-learn, LightGBM, Model Evaluation, XGBoost, Benchmarking, Cloud Platforms, A/B Testing, RAG Pipelines, Recommendation Systems, Embedding Models, Data Pipelines, Data Modeling, Microservices, Model Context Protocol (MCP), Claude Code, Harness, Hugging Face Transformers, RAG Architecture, Technical Writing, Artificial Intelligence as a Service (AIaaS), Claude, Gemini, AI Chatbots, Chatbots, Automation, Microsoft Copilot, Technology
ML Expert/Teaching Assistant
2022 - 2024
Sabanci University
- Assisted in teaching the Introduction to Programming course, guiding 100+ students through core Python concepts, grading assignments, conducting weekly lab sessions, and providing one-on-one mentoring.
- Supported the Introduction to Data Science course by preparing hands-on lab materials covering Scikit-learn and Pandas, evaluating ML projects, and mentoring students through data preprocessing and model evaluation.
- Facilitated a data visualization and analysis course, helping students master Matplotlib and Seaborn, reviewing capstone project submissions, and delivering supplementary sessions on effective data storytelling.
Technologies: Python, PyTorch, TensorFlow, Scikit-learn, Large Language Models (LLMs), High-performance Computing (HPC), Pandas, NumPy, Agentic AI, Generative Artificial Intelligence (GenAI), Hyperparameter Tuning, API Integration, Software Architecture, Imbalanced-learn, LightGBM, Model Evaluation, XGBoost, Cloud Platforms, Automation
Data Scientist
2021 - 2022
Eksim Holding
- Developed machine learning models for detecting electrical leaks across Eksim Holding's energy infrastructure, applying anomaly detection algorithms and feature engineering techniques to identify consumption patterns with high precision.
- Built end-to-end data pipelines for ML projects, handling data collection, cleaning, transformation, and validation processes to ensure high-quality training datasets, reducing data preparation time and enabling faster model iteration cycles.
- Designed advanced SQL stored procedures and optimized database queries to support rapid data retrieval and processing for ML workflows, improving data accessibility and enabling real-time analytics across energy monitoring systems at scale.
Technologies: Python, SQL, Data Science, Machine Learning, Pandas, NumPy, Agentic AI, Generative Artificial Intelligence (GenAI), Software Architecture, Imbalanced-learn, LightGBM, Model Evaluation, XGBoost
Experience
A Synergistic Multi-stage RAG Architecture for Boosting Context Relevance in Data Science Literature
https://www.sciencedirect.com/science/article/pii/S294971912500055XThis project was published in the Natural Language Processing Journal, Elsevier. Based on my master's thesis, this work presents a novel multi-stage RAG system integrating structured document parsing, domain-specific embedding fine-tuning, semantic chunking, and an "Abstract First" retrieval strategy, achieving an over 15-fold improvement in context relevance for navigating data science literature.
Essay Evaluator
https://github.com/Ahmetyasin/Essay_EvaluatorAn improved essay evaluation system that leverages fine-tuned language models and optimized prompting techniques to provide accurate, rubric-based essay scoring. The project includes enhanced prompt engineering with emotional stimuli and reward elements.
Synthetic Data Generator Evaluative Visualization Tool
https://ieeexplore.ieee.org/document/11111841This work introduces a tool that visualizes GAN model losses and performance metrics in real time, enabling progressive training expansion with dynamic dataset sampling to improve hyperparameter tuning and convergence speed. It was published in the 33rd IEEE Conference on Signal Processing and Communications Applications.
Fine-tuned Large Language Model for Recommendation Tasks
https://github.com/Ahmetyasin/LLM-Based_Recommendation_SystemI improved recommendation system performance by fine-tuning an LLM using Alpaca-LoRA for parameter-efficient training, leveraging cosine similarity for item ranking, and surpassing traditional collaborative filtering benchmarks in accuracy and relevance.
Sectoral Growth Prediction Using Macroeconomic Indicators
https://github.com/Ahmetyasin/Predicting-Sectoral-Growth-Using-Macroeconomics-IndicatorsI enhanced the prediction accuracy of sectoral growth rates by employing machine learning to analyze macroeconomic indicators from the Turkish Central Bank and TUIK, reducing the mean absolute error from 0.70 to 0.28.
Education
2025 - 2026
PhD in Data Science and AI
Bogazici University - Turkey
2022 - 2024
Master's Degree in Data Science and AI
Sabanci University - Turkey
2016 - 2018
Bachelor's Degree in Mechanical Engineering
Bogazici University - Turkey
2016 - 2018
Bachelor's Degree in Electrical Engineering
Middle East Technical University - Turkey
Certifications
SEPTEMBER 2024 - SEPTEMBER 2027
AWS Certified Solutions Architect Associate
Amazon Web Services
Skills
Libraries/APIs
Scikit-learn, PyTorch, vLLM, Pandas, NumPy, Imbalanced-learn, XGBoost, Hugging Face Transformers, TensorFlow
Tools
Azure DevOps Services, Git, GitHub, Claude Code, Claude, Microsoft Copilot, Azure OpenAI Service, Apache Airflow
Languages
Python, SQL
Frameworks
LangGraph, Agentic Frameworks, LightGBM
Paradigms
REST, ETL, Microservices, Model Context Protocol (MCP), Automation, High-performance Computing (HPC)
Platforms
Jupyter Notebook, Docker, AWS IoT, Ollama, Amazon Web Services (AWS), Microsoft Copilot Studio, Harness, Linux, Azure
Industry Expertise
Bioinformatics
Storage
Data Pipelines, Redis, Elasticsearch
Other
Retrieval-augmented Generation (RAG), Large Language Models (LLMs), AI Agents, Artificial Intelligence (AI), Data Science, Machine Learning, LangChain, FastAPI, Pinecone, Fine-tuning, Natural Language Processing (NLP), Semantic Search, Agentic AI, AI Architecture, Large Language Model Operations (LLMOps), Graphics Processing Unit (GPU), AI Model Training, Generative Artificial Intelligence (GenAI), RAG Systems, Prompt Engineering, OpenAI, Anthropic, Vector Databases, Hyperparameter Tuning, API Integration, AI Agent Orchestration, AI Integration, APIs, Software Architecture, Architecture, Data Analytics, Data Analysis, Forecasting, Agentic AI Systems, Model Evaluation, Benchmarking, Cloud Platforms, A/B Testing, RAG Pipelines, Recommendation Systems, Embedding Models, Data Modeling, RAG Architecture, Technical Writing, Artificial Intelligence as a Service (AIaaS), Gemini, AI Chatbots, Chatbots, Technology, Machine Learning Operations (MLOps), Milvus, MLflow
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