Services

AI engineering, start to production.

I take on a small number of projects at a time and lead each one myself. Most start with AI. All of them end with something running in production.

How a project runs

Demos are easy. Production is the job.

I work as a forward deployed engineer: inside your team, close to the people who'll use what we build, and on your hours.

01
Sit with the workflow
Before any code, I watch how the work gets done today. Who touches it, where it breaks, and what "done" means for the business, not just for the ticket.
02
Scope what's real
A short written plan: what we'll build, what we won't, and how we'll know it works. AI projects fail on vague scope far more often than on bad models.
03
Build and ship
Small releases in front of real users, early. You see working software every week, not a status report.
04
Stay through production
Live systems break in ways demos don't. I stay for the messy part: debugging live, shifting requirements, the integration nobody documented.

Contact

I read every message myself and usually reply the same day. A rough idea is enough to start.

Hours

I keep flexible hours and move my day to overlap with yours, whether that's a morning standup in New York or a late release in Sydney.