Architecture review & code audit
A close read of an existing system: the risks, what's worth changing, and the smallest changes with the biggest effect.
Self-hosted LLMs
Running open models on your own hardware: sizing, quantization, serving, and an evaluation on your own tasks before you commit.
LLM classification & routing
Using LLMs to make decisions rather than write text: routing, classification, scoring and guardrails, with a test set to measure them.
Advisory retainer
A few hours a month of async reviews and second opinions, for teams that want an outside senior engineer to check their thinking.
How it works
- Email a few lines about the problem.
- Short call to check it's a good fit.
- Written proposal with fixed scope, timeline and price.
- Delivery with check-ins along the way and a handover at the end.
Track record
- 1M+ monthly users on a ticketing platform kept within its downtime SLA
- 3–4 h → 15 min release time after replacing manual deploys with CI
- 12+ years across finance, aviation, public sector and ticketing
Products I've shipped
hellow: unified chat for streamers across Kick, TikTok, Twitch and YouTube. Designed, built and run end to end, including the paid plan.