I am currently a Visiting Research Scientist at Google Deepmind.  In Spring 2026, I will start as an Assistant Professor in the Psychology Department at NYU, where my lab will study questions at the intersection of the cognitive of science of human moral judgment and AI safety.

I use the tools and methods of cognitive science to help engineer AI systems to be better aligned with the plurality of human moral values, while also being interpretable and steerable.  My work also engages with contemporary moral philosophy and seeks to fundamentally understand how the human moral mind works in computational terms.

Previously, I was a Research Scientist at the Allen Institute for AI focusing on AI safety.  I completed my PhD in the Rutgers University Department of Psychology and Center for Cognitive Science.  My dissertation was supervised by Alan Leslie in the Cognitive Development Lab on the the topic of moral rules and representations.  I then held a joint appointment as a postdoc at the Harvard Psychology Department (supervised by Fiery Cushman) and the MIT Brain and Cognitive Sciences Department (supervised by Joshua Tenenbaum).  I maintain Research Affiliate status with both Harvard and MIT.

Full academic CV available here.