Contributing physician reviewer for the Penda Health and OpenAI AI Consult study. Supported evaluation efforts by grading clinical documentation quality and identifying errors. This work helped verify study results.

Contributing physician in OpenAI’s HealthBench evaluation. Contributed to advanced human data initiatives for OpenAI, designed to improve the safety of AI models on health-related questions. Responsibilities included evaluating the accuracy and quality of model-generated health-related responses. These efforts helped ensure the safety of AI solutions.