- 🏗️ Focus: Production-grade GenAI (RAG, agents, evals, observability)
- 🔍 Currently: Retrieval tuning (chunking, re-ranking, hybrid search) + workflow orchestration
- 🤝 Open to: OSS in vector search, LLM tooling, eval frameworks, agent runtimes
- 💬 Happy to chat: embeddings, RAG design, deployment, CI/CD, cost/latency tradeoffs
- ⚡ Principle: Clean abstractions > fancy demos
I optimize for: measurable quality, predictable latency, and operational simplicity.


