Work
Federal regulatory filings, generated on the client's own hardware
Mistral and Llama served inside a US healthcare provider's network behind an ASP.NET Core backend. Patient data never left their infrastructure.
A patient-facing RAG chatbot that books, charges and routes
Production system for a US healthcare team. Answers grounded in their own documents with traceable retrieval, and it escalates to a person before anything clinical.
Motivia — generative media platform, live in production
Seven generation types, GPU inference behind a queue with retry, server-side video compositing. Built and running with paying subscribers.
Document extraction that runs where the documents already are
Vision-language models served locally, reading layout, tables and handwriting at 83 tokens per second. For documents that can't reach a cloud API, and volumes where per-page pricing breaks.
A coursework platform that replaced the spreadsheets
Submissions, marking and moderation moved off shared spreadsheets for a European university. Next.js and React front end, FastAPI and PostgreSQL behind.
Agents that take actions, running entirely on local hardware
Desktop agents that run shell commands, manage files and drive coding sessions, with speech handled on-device. Built to work out where an agent should be allowed to act.