Mei-Lin Zhou
ML platform engineer
Engineering team profile. AI/MLOps posts on AI-DE Insights cover RAG architecture (chunking strategies, hybrid retrieval, cross-encoder reranking, RAGAS evaluation), cost-efficient inference, and the LLM routing + caching tiers that actually move bills down. Replace with real bio when authoring identity ships.
2 posts by this author
- AI/MLOpsApr 15, 202615 min readBuild an AI Tactical Analyst with NFL Data, dbt, and RAG: A Full Data Engineering Pipeline
While everyone else argues about the halftime show, we're building the scouting report. This tutorial walks through a full end-to-end data + AI pipeline using NFL play-by-play data, dbt, and a RAG-powered analyst.
- AI/MLOpsMar 04, 20269 min readBuilding a Cost-Efficient RAG Pipeline with Pinecone
RAG pipelines can get expensive fast: embedding costs, vector storage costs, LLM inference costs. After running our production RAG system for 9 months, we cut costs by 73% with three architectural changes. None of them involve switching models.