I am an AI PhD student at UC Berkeley, researching reinforcement learning, reward modeling and model misspecification with the Center for Human Compatible Artifical Intelligence (CHAI) and advised by Professor Stuart Russell. I graduated Phi Beta Kappa from Duke University in 2017 with an interdepartmental BA in "Artificial Intelligence Systems". As an undergraduate, I studied computer science, neuroscience and philosophy at both Duke University and the University of North Carolina at Chapel Hill through the Robertson Scholars Leadership Program, and at Oxford University as a Registered Visiting Student. My previous research involved incorporating moral values into a kidney exchange algorithm as part of the Duke Moral AI research group, supervised by Professor Vince Conitzer. I am very grateful to be supported by an EECS Excellence Award.