PhD-trained engineer building production AI applications with Python, Django, and modern LLM tooling. I take AI projects from prototype to shipped product — RAG systems, agents, custom integrations, and the full-stack web or desktop applications that wrap them.
What I'm hired for:
- LLM application engineering — RAG pipelines, multi-step agents, custom evaluation harnesses, OpenAI / Anthropic / open-source model integration, structured output and tool use, prompt and retrieval optimization
- Django & FastAPI backends for AI products — auth, billing, async job queues, streaming responses, vector stores (pgvector, Qdrant, Chroma), observability for LLM calls
- AI-powered desktop applications — Tauri (Rust) and PyQt5 for clients who need offline-capable, on-prem, or data-sensitive tools. A rare combination: most AI engineers can't ship desktop; most desktop developers can't ship AI
- Scientific and R&D software — instrumentation control, data pipelines, numerical analysis. Background suited to biotech, hardware, and research-driven startups
Background:
- PhD in Electrical Engineering, University of Southampton (2022)
- 2,300+ hours and $100K+ delivered on Upwork. Top Rated, 100% Job Success
- Roles at two scientific instrumentation startups (Lightcast Discovery, CellCraft)
Core stack: Python, Rust, Django, FastAPI, HTMX, PostgreSQL + pgvector, Docker, Kubernetes, AWS, OpenAI/Anthropic APIs, Tauri, PyQt5.
I work best with founders and small teams who want someone senior — someone who'll push back on bad ideas, ship clean code, and stay with the project until it works in production, not just in a demo.