About
I’m the COO at Pelloran, where we’re building infrastructure for trustworthy and verifiable intelligence. Our work focuses on AI memory, reasoning, provenance, and deterministic inference. Current initiatives include KELVIN, KELVIN ZERO, and tritify — Pelloran’s open-source project for deterministic and reproducible AI inference. With tritify, we’re exploring how one AI model can run across multiple machines while keeping execution reproducible and independently verifiable. Interested in open-source AI, inference infrastructure, reproducibility, and systems that can prove what they know.
Links
Badges
