What Happens After You Call an LLM?
A production engineer's tour through the infrastructure behind a seemingly simple AI request.
A small moment of calm
Add as many little saplings as you like. There is no score, streak, or pressure to keep going.
0 saplings added
Just an illustration: these digital saplings do not plant real trees or offset emissions.
Publication
How AI actually works in production. Practical engineering notes on inference, GPUs, model serving, reliability, observability, and AI platforms.
Explore the publicationConversations and presentations on production engineering, AI infrastructure, and the systems behind modern AI.
Explore talks