@sailokesh8
About
AI/ML & MLOps Engineer. I build production pipelines and LLM systems. Writing about real-world AI engineering.
Available for
Nothing here yet.
Devathi Sai Lokesh's blogs
Recently published
RAG is Not Just Chunking + Embedding + Retrieval — Here's What Production Actually Looks Like
6d ago · 6 min read · Most engineers learn RAG like this: Chunk → Embed → Store → Retrieve → LLM → Done. That works for a weekend project. It fails at 10M+ documents in production. Here's what production RAG actually looks
Join discussion