Architecting an AI Inference Stack
· 6 min read
Notes on architecting AI inference stacks and TPUs from Google's learning path, "Inference on TPUs".

Notes on architecting AI inference stacks and TPUs from Google's learning path, "Inference on TPUs".

Notes on architecting multi-agent systems from Google's learning path, "Architect Multi-Agent Systems with Agent Development Kit".

Notes from the classic 1987 paper from Birman and Joseph on Virtual Synchrony, a computation model for distributed systems.

Notes on "CAPO: Cost Aware Prompt Optimization" (June 2025) from the Munich Center for Machine Learning.
