Building production ML inference systems · Google Dev Group Organizer · Speaker · OSS contributor
I work on ML inference systems at Trendyol, where I help deploy and optimize the platform that serves recommendation engines, search ranking, and increasingly AI agents in production.
My work sits at the intersection of ML, systems, and infrastructure — vLLM and Triton for serving, Kubernetes across cloud and on-prem, and Piper, our in-house orchestration system. I care about the parts of ML that don't make it into most conference talks: p99 latency, GPU utilization, what breaks at 3am.
I co-organize GDG Istanbul and speak regularly at DevFest, Build with AI, and GDG events across Turkey and abroad.