I am an incoming National Library of Medicine fellow at Columbia's Department of Biomedical Informatics!

I develop machine learning methods for health, guided by a broad question: how can we embed AI systems effectively within human systems? In healthcare, this means reasoning about how people and institutions shape the development and deployment of AI: how patients seek care, how clinicians make decisions, how incentives shape recorded data. My recent work develops methods to audit the data used to train AI systems (NWH 2024; JAMA HF 2026); to evaluate systems when labels are limited or unreliable (CHI 2023; NeurIPS 2025); and to improve the reliability of pretrained systems at test time (ICCV 2021; CVPR 2025). I am always excited to work with students and collaborators on problems where real clinical settings reveal new technical questions.

I am currently a postdoc at Cornell Tech, working with Emma Pierson and Jenna Wiens. I completed my Ph.D. at MIT, where I was lucky to be advised by John Guttag.