Backend engineer with 2.5+ years across Python/Django, Node/Express, and .NET, now focused full-time on LLM application engineering. I solo-built HRPilot, a multi-tenant HR and payroll platform with 78 data models and 305 REST endpoints, shipped in 77 days as the sole contributor. It includes a RAG layer over pgvector with tenant-isolated retrieval, a custom Model Context Protocol (MCP) server exposing 12 typed tools, and a golden-set evaluation harness using LLM-as-a-judge to score tool-invocation correctness and hallucination.
I care most about the engineering discipline behind AI features — tenant isolation at the query level, cost/latency profiling instead of guesswork, and evaluation numbers instead of vibes. Outside HRPilot, I co-founded Kreatech Hub, where I've delivered 6 client projects end to end, and I previously built production ERP and REST API systems in ASP.NET and Django.
I'm looking for remote AI engineering roles — especially teams building RAG, agentic tooling, or LLM infrastructure — where I can own systems from schema design through deployment.
