Blog

Writing on the infrastructure layer of LLM systems — inference cost, serving, retrieval, evals, and observability. Mostly what I’ve measured, and what surprised me.

2026

Hybrid search didn't help. It still fixed my retrieval.

12 August 2026

Technology Ritam Rag Retrieval Evals Inference-Cost LLM

I added hybrid search and a cross-encoder reranker to my RAG service, measured it, and wrote up four findings. Then I ran the one comparison I’d been putting off, and three of the four didn’t survive.

Building a RAG service: architecture, trade-offs, and lessons

29 January 2026·9 mins

Technology Ritam Rag Fastapi GCP Observability LLM

Built a production-shaped RAG v1: offline indexing + FastAPI /query on Cloud Run (Terraform), with sources, logs, and basic monitoring.