ai engineering
Python, ML/DL, data processing and production-focused model deployment.
Building reliable AI & .NET systems with measurable impact.

I build AI and software that ships. LLM-powered products, real-time computer-vision systems running in the field today, .NET and Python backends, Flutter mobile apps — and the Docker/CI-CD pipelines that put them all live. I take an idea end to end: design it, build it, run it in production.
Python, ML/DL, data processing and production-focused model deployment.
High-performance, reliable REST/GraphQL services with .NET and FastAPI.
Docker, CI/CD, monitoring—ensuring models are stable and trackable in production.

🟢 A C#/.NET system I built in the defense domain, actively used in the field. Built on camera and device SDK integrations with a multi-module architecture. (Operational details are confidential.)

The site you're looking at: a multi-service bilingual CV/portfolio built with Next.js + FastAPI + PostgreSQL, containerized with Docker behind Traefik — blog & project management from an admin panel, with CI/CD.

Site and online market for a Korean restaurant chain. Turkish and English, with cart and checkout.

Not a bot with canned answers but a tool-using agent: a WhatsApp/Instagram assistant on LangGraph + FastAPI that creates real orders while it talks, runs channel-agnostically and hands off to a human when it should.

How I split this site from a single app into three services — database, API and frontend — and bring them all up with one command.

The browser never sees the backend. I explain the Backend-for-Frontend pattern: keeping the JWT in an httpOnly cookie and talking to the API only from the server.