Senior AI Engineer (architecture-focused) with 7+ years of experience building and operating production AI systems at scale. I specialize in production LLMs, scalable ML infrastructure, and end-to-end system design under real-world latency and cost constraints.

My work spans the full AI lifecycle from research to production, with a strong focus on reliability, retrieval quality, and system-level trade-offs.

Current interests: Production RAG systems, hybrid retrieval, multi-agent architectures, and AI interpretability in real-world systems.