James Petrie
This stream works on verifying what AI hardware is actually running, through zero-knowledge proofs of AI workloads and FPGA development for an inference-verification prototype. Projects extend that prototype and develop new protocols for hardware verification.
Stream overview
- Zero knowledge proofs of AI workloads, e.g. the Future Work section in the readme here: https://github.com/JamesPetrie/verinf
- FPGA logic development for our inference verification prototype with SASH: https://www.aisafety.sg/blog/making-ai-verification-international (e.g. formal verification of the logic, switching to an fpga with higher bandwidth, developing a protocol for outside-of-cluster verified memory)
- Hardware verification research and development (e.g. developing new protocols for verification): https://docs.google.com/document/d/11GlVlGlR2sR64PmYqjsjuWgX-vl2wfIAmO2x0a-GU7Q/edit?tab=t.0#heading=h.iaihcqkzjpi5
Mentors
James is Compute Security and Governance Lead at the Future of Life Institute and a Research Affiliate with the Oxford Martin AI Governance Initiative. His current research focuses on verifying how AI compute is used: designing verification protocols, prototyping zero-knowledge proofs of inference, and prototyping network certifier hardware. Previously, he completed a PhD in Applied Mathematics based on his work during the COVID-19 pandemic building the first decentralized digital contact tracing system. He also has a Master's Degree in Computational Mathematics, a Bachelor's Degree in Engineering Physics, and worked as a Firmware Engineer at Intel.
Mentorship style
Fellows we are looking for
Project selection
The Winter 2027 cohort offers a wide range of research streams led by experts across AI alignment, interpretability, governance, and safety. Each stream provides its own research agenda, methodology, and mentorship focus.
