I am a Ph.D. student, co-advised by Pavel Izmailov at NYU and Saadia Gabriel at UCLA.

I am also a Student Researcher at Google DeepMind.

My research focuses on scalable supervision: methods for aligning AI systems that are becoming more capable than humans.

I am also interested in how reasoning emerges in language models, from pre-training to post-training.

Previously, I interned at Google Research on the scientific discovery team, Amazon's AGI RL Reasoning team, and Apple's machine learning team. Before UCLA, I worked at NYU on scalable oversight and AI safety.