Principal AI Engineer

I build systems
where humans
stay in control.

Production LLM systems designed around real product constraints, not just model capabilities. Augmenting people, not replacing them.

50+ AI products shipped
150M+ User scale
~$20M Revenue impact
<2s Agent latency
Selected work
Perspective

Technology should augment people, not replace them.

I'm not a tech evangelist or a luddite. The question isn't how fast we automate — it's how we evolve with technology without losing ourselves.

one

Start from constraints

User needs first, model is a detail.

two

Make the workflow explicit

State, routing, evaluation, observability.

three

Keep humans in control

Automation where it earns its place.

Exocore

A personal context system — capturing inputs, structuring them into tasks, memory, and decisions. Not autonomous. Human-in-the-loop by design.