I'm an engineer who ships LLM-powered product features end to end, with 8+ years of full-stack delivery behind me. I design retrieval and agent-style workflows, integrate OpenAI and Anthropic (and similar) APIs, and care about the whole production story: latency, cost, safety, and observability-not only the demo. I build the surrounding software the same way: React and TypeScript on the front, .NET and Python (FastAPI, Django) on the back, and AWS/Firebase in the cloud. That background matters when AI has to sit inside real auth, billing, data policies, and scale. What sets me apart: - Hands-on with LangChain, OpenAI, Anthropic, and common patterns for RAG, tool use, and structured outputs - Vector database experience for production RAG: embedding pipelines, chunking and metadata strategy, hybrid search, and tuning recall/latency across stores like Pinecone, Weaviate, pgvector, and Chroma - MCP (Model Context Protocol) for connecting models to real tools and data: designing MCP servers, exposing internal APIs and databases safely, and wiring agent workflows that stay maintainable as integrations grow - Production mindset: evals and guardrails, prompt versioning, streaming UX, token and rate-limit discipline, logging and tracing around model calls - Strong general engineering: TypeScript, .NET, Python, REST and real-time APIs, payments and integrations - Experience mentoring, raising code quality, and working with product on measurable outcomes I work with product and stakeholders to turn ambiguous AI ideas into shipped, maintainable features.