Mert Sırakaya - Python & Applied AI Engineer

Mert Sırakaya

Applied AI Engineer | Python | FastAPI

Get in touch | Istanbul, Türkiye | contact@tomris.dev

§ fswair | ï mert-sirakaya |  tomris.dev | 3 swair | Å edulayer

Intro

Applied AI Engineer and Python Developer specializing in collaborative open-source de-

velopment and the design of production-grade agentic systems. I build reliable agents using Py-

dantic AI, contributing to the core project through cross-functional collaboration and upstream

PRs. My work emphasizes problem solving via AI observability (Logﬁre), rigorous evaluation,

and structured documentation. Committed to knowledge sharing, I produce technical deep-dives

in C++ and Python for the developer community.

Current Focus

I bridge the gap between LLMs and production by integrating automated AI evaluations into TDD

workﬂows as a ﬁrst-class testing mechanism. In my framework, I engineered runtime recovery and self-

healing capabilities, allowing tools to self-correct via context-aware retries and dynamic dependency

injection. I specialize in agent systems driven by evaluation and runtime reliability. Parallel to

this, I apply advanced prompt optimization techniques using DSPy/GEPA. My focus remains on

advancing the agent runtime infrastructure for fully production-ready systems.

Experience

Python Engineer Jun 2022 – Present

Contract Remote

Managed the full software development lifecycle (SDLC), translating complex client requirements

into scalable Python automation and Web3 solutions. Architected a high-concurrency production Web3

API used by 250+ clients, handling 2M+ edge requests with FastAPI. Optimized endpoints to maintain

400ms latency and 99.2% uptime under heavy load. Built robust ETL pipelines for data aggregation

and developed asynchronous Telegram bots, ensuring high availability through proactive troubleshooting

and optimization. Utilized custom ORM tools (MentoDB) to streamline database interactions.

Projects

VOWEL (3k+ Downloads) | Nov 2025 – Present

Built declarative YAML speciﬁcation language and framework for testing and evaluating Python

functions with AI-powered eval spec auto-generation. Supports pytest patterns such as ﬁxtures and

parametrization. Generating and running AI-generated evaluations took under eight seconds and costs

about half a cent per function.

pypi.org/project/vowel

VenusAI (4.5k Downloads) | May 2025 – Present

Developing an extended Pydantic AI fork focused on building more capable AI agents — adding dynamic

tool management, error-safe and self-healing tool execution, sandboxed execution, multi-backend caching, and

seamless MCP integration. Designed comprehensive documentation to support developer adoption.

pypi.org/project/venai

MentoDB (5k+ Downloads) | Jun 2022

Built an ORM mount for SQL engines that supports various output formats, including Pandas DataFrames

and JSON-based structures. Provides Pydantic integration and allows direct access to raw SQL connec-

tions. Used in freelance client projects for local database integrations.

pypi.org/project/mentodb

Skills

Python: OOP, FastAPI, Scraping & Automation, Backend, PyPI, Typed, PEP8, Async Programming

PydanticAI: Agents, Graphs, Tool Calling, Embeddings, AI Evals

DSpy: Signatures, Prediction, LLMs, GEPA

Logﬁre: Observability, Monitoring, Debugging, AI Observability

Large Language Models: Groq, Ollama, LM Studio, Google AI Studio, OCR, RAG, Prompt Optimization

Vector Databases: ChromaDB, RAG, Embeddings, Chunking

n8n: AI Workﬂows, Workﬂow Automations

Pydantic: Data Validation, JSON Schema, Serialization

TDD: Pytest, Mocks, Fixtures, Unit Testing

CI/CD: AWS, CloudWatch, Lambda, Nginx, Docker, GitHub Actions, Vercel

C++: OOP, STL, Generics, C++20, Modern C++, Iterators

Databases: SQL, SQLite, SQLAlchemy, MongoDB (NoSQL, Aggregation, Modeling)

Certiﬁcations

MongoDB Python Developer Path – MongoDB Academia (March 2025)

The C++ Programming Language – Plepa Training & Consulting (July 2023 - January 2024)

Education

Istanbul University Aug 2023 – Jan 2026

Associate (OEF), Web Design and Development GPA: 3.41

Languages

Turkish (Native Speaker), English (Professional Working Proﬁciency)