Hi! I’m an A.I. researcher, academic, and entrepreneur, based in San Francisco, California. In 2026 I co-founded Elorian (with Andrew Dai and Yinfei Yang), where we are building frontier visual thinking models. Prior to that I co-founded Welligence (with Ross Lubetkin and Ivan Cima) and served as CTO for the first five years of the company (130+ FTEs today), was a researcher on the Gemini Data team at google, and was an assistant professor at Harvard from 2021-2026, where my lab focused on data-centric A.I. I earned my PhD from UPenn in 2020 under the supervision of the great Michael Kearns and Aaron Roth, and my pure math degree from Harvard (math 55 alum). The research I’m most known for includes: the first SFT-based method for knowledge removal from models, the first algorithm with “provable” guarantees for learning an unbiased model with respect to exponentially many protected groups, the best known bounds connecting differential privacy and adaptive data analysis, and investigating the privacy properties of LLMs.