Production AI applications in Python & Rust — RAG pipelines, agents, Django/FastAPI backends, on-prem desktop clients
PhD-trained engineer building production AI applications with Python, Django, and modern LLM tooling. I take projects from prototype to shipped product — RAG pipelines, multi-step agents, custom evaluation harnesses, and structured tool use, integrated with OpenAI, Anthropic, or open-source models. I build the backends that make them real: auth, billing, async job queues, streaming responses, and vector stores like pgvector, Qdrant, and Chroma. When the data can't leave the building, I ship offline-capable desktop clients in Tauri and PyQt5 — a rare combination, since most AI engineers can't ship desktop and most desktop developers can't ship AI. My background in scientific instrumentation and R&D suits biotech, hardware, and research-driven startups that need someone genuinely senior.
Work Terms
- Rate: $55/hr; longer engagements preferred over one-off tasks.
- Best fit: founders and small teams who want a senior engineer, not just an extra pair of hands.
- How I work: I push back on bad ideas, ship clean and tested code, and stay through to production.
- Getting started: share a short description of your project and your goals, and we'll scope it together.