Writing
Notes on LLM infrastructure, GPU capacity, and observability, from building and running real systems.
October 9, 2026
Conversation Engineering
The data science behind a live assistant that answers from what you actually know
October 9, 2026
The Interview Copilot Epidemic
Two dozen products built around one promise, that nobody will know
October 6, 2026
What Changes When the Thing You Monitor Is an LLM
Notes from an observability engineer running his own inference service
October 5, 2026
Holding Long Conversations in GPU Memory
Capacity engineering for a self-hosted, real-time LLM service on vLLM and Nemotron 3 Nano
June 17, 2026
Fine-Tuning Qwen3-32B on 16 H200s with Slurm on Kubernetes
Field notes from a function-calling PoC on Nebius Soperator: what worked, what bit me, and where it fits