Geoffrey Irving
Affiliations
Chief Scientist, UK AI Security Institute
Biography
Geoffrey Irving is Chief Scientist at the UK AI Security Institute. Previously Geoffrey led the Scalable Alignment Team at DeepMind, covering both broad AGI safety efforts and large language model safety specifically. Before that, he led the Reflection Team at OpenAI, co-led the N2Formal neural network theorem proving effort in Google Brain, and worked on computational physics and geometry at Otherlab, D. E. Shaw Research, Pixar, and Weta Digital. Geoffrey has a Ph.D. in computer science from Stanford University, and screen credits on Ratatouille, WALL•E, Up, and Tintin.