Summary
Chris Cundy is a research scientist at FAR AI with a decade of experience applying rigorous ML and physics training to reduce catastrophic risks from advanced AI systems. He holds a PhD from Stanford (advised by Stefano Ermon) and dual degrees from Cambridge, where his work spanned Gaussian Process state-space models and variational inference for dynamical systems. His research blends preference learning, inverse reinforcement learning, and human judgement aggregation—skills honed at UC Berkeley and Oxford’s Future of Humanity Institute—to make AI behaviour more robust, predictable, and aligned with broadly distributed benefits. Chris pairs strong theoretical foundations with practical engineering (from Raspberry Pi energy-monitoring to web automation and data-driven process optimisations), reflecting an aptitude for turning complex research into deployable tools. Based in San Francisco, he focuses on pragmatic, safety-oriented methods that anticipate worst-case harms rather than only average-case performance.
10 years of coding experience
1 year of employment as a software developer
Simon Langton Grammar School for Boys
Master’s Degree Computer Science, Master’s Degree Computer Science at University of Cambridge
Doctor of Philosophy - PhD Computer Science, Doctor of Philosophy - PhD Computer Science at Stanford University
Spanish