Umut ABALI

Hey, I'm UMUT

Engineer · Istanbul

I build full-stack apps, data pipelines, and agentic AI systems. Focused on LLMOps, RL, inference, and local LLMs.

The systems are written up under projects and on the blog. Code is on GitHub. Work, school, and skills are on my resume.

More about me

Recent projects

  • Mini-CDN

    Built a CDN simulation with three edge cache nodes, round-robin routing, TTL/LRU caching, and Prometheus/Grafana monitoring.

    Deep diveCode

  • Turkish Gemma-4 Fine-tune

    Fine-tuned Gemma-4-E4B on 3,000 Turkish RAG examples, training 0.23% of parameters in about 42 minutes on an A100, and published LoRA, 16-bit, and GGUF versions on Hugging Face.

    Deep diveCodeDemo

  • Agentic RAG System

    Built a multi-agent RAG platform with a LangGraph supervisor, hybrid retrieval (dense + BM25 + cross-encoder reranking), and Qwen served on vLLM, deployed with Docker, Redis, Postgres, and JWT auth.

    Deep diveCode