Research Scientist at J.P. Morgan's Explainable AI Center of Excellence, working to build aligned and interpretable AI.
Education
PhD from the University of Bristol and Alan Turing Institute, focusing on both interpretability and alignment problems, particularly in reinforcement learning agents.
Background
AI researcher working at the intersection of interpretability and alignment, with a focus on reinforcement learning agents. Currently expanding scope to work on other kinds of AI systems, including language models.
Miscellany
Connect: Email, Twitter, LinkedIn, Github, Google Scholar