Skip to content
View omarcevi's full-sized avatar
🎯
Focusing
🎯
Focusing

Highlights

  • Pro

Block or report omarcevi

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
omarcevi/README.md

Hey, I'm Omar 👋

I work on the part of ML that comes after training: serving models fast, turning them into agents, and checking that they actually work. At Trendyol I ran model serving for 100M+ users with Triton and vLLM. On my own, I build AI agents with Google ADK and take them all the way to production.

Google Developer Expert, Cloud AI · GDG Istanbul co-organizer · Istanbul

Python, Kubernetes, Docker, Google Cloud, Terraform, GitHub Actions
Plus NVIDIA Triton · vLLM · Google ADK

🔨 Things I've built

🧪 Things I measured

  • A single agent matched a planner + coder + reviewer team on 15 coding tasks (36 vs 34 of 45 runs solved) and cost less per run. sdlc-agent-pipeline
  • At the same average rate, bursty traffic made vLLM's time to first token about 5× worse than steady traffic. vllm-metal-bench
  • Splitting H100s between models with MIG gave about 1.75× more serving capacity. One H100, Many Models

🎤 Speaking

Next: Retrieval Is All You Need (Almost) · DevFest İzmir 2026 · 5 December 2026

All talks and workshops →

✍️ Writing

🤝 Open source

My GitHub contributions drawn as a 3D city

omarcevi.dev · LinkedIn · Medium · hello@omarcevi.dev

Pinned Loading

  1. sdlc-agent-pipeline sdlc-agent-pipeline Public

    Multi-agent pipeline (Google ADK 2.x) that turns a GitHub issue into a tested pull request, measured on a hidden-test benchmark

    Python 1

  2. vllm-metal-bench vllm-metal-bench Public

    vllm-metal + AIPerf benchmark on an M1 Pro 16GB: p99 TTFT knee, MTP on/off, Poisson vs bursty arrivals, 4 models

    Python

  3. augury augury Public

    Augury: a terminal-native AI digest reader.

    Python 1

  4. claudemods claudemods Public

    Community Claude mods, plugins & skills, installable from one marketplace

    HTML 11 5

  5. adk-evaluation-demo adk-evaluation-demo Public

    Python 2

  6. trabzonspor_analyst trabzonspor_analyst Public

    DevFest Trabzon 2026: five agent patterns with Google ADK on real Trabzonspor vs Gaziantep FK data

    Python 1