Applied AI — Local LLMs & RAG
I build privacy-first AI systems — local large language models and retrieval-augmented generation — that give you the capability of modern AI without your data ever leaving your own infrastructure.
What I deliver
Local LLM deployment
Capable language models running on your own GPU or servers, with zero cloud exposure.
RAG over private documents
Semantic search and grounded answers across your own confidential files.
Query engines & routing
Multi-route pipelines tuned to how your team actually asks questions.
Evaluation & guardrails
Measurable accuracy and safe, auditable outputs you can trust.
How I work
Discovery
We start with the decision you need to make, the data you hold, and what a good outcome looks like.
Scope
A clear, fixed-scope proposal with defined deliverables and success criteria — no open-ended billing.
Build
Modelling, validation and iteration against your real data, with progress you can see.
Handover
Production-ready code, documentation and a dashboard or interface your team can actually use.
Capabilities & tools
Selected related work
Have a project in mind?
Tell me about the decision you're trying to make with your data. I'll tell you honestly whether I can help.
Get in touch