Writing
Notes on building AI systems.
Technical deep-dives on RAG, local inference, and production ML — the stuff I wish someone had written when I was figuring it out.
Nov 12, 20258 min read
Building Production-Grade RAG Pipelines
Lessons learned from shipping retrieval-augmented generation systems that actually hold up under real query load.
RAGLLMArchitecture
Sep 28, 20256 min read
Why I Moved My LLMs to Local Inference
The case for running large language models on your own hardware — and the engineering it actually takes to pull it off.
LLMInferenceInfrastructure