I work on opening the black box of generative AI: understanding what large models have learned, why they answered the way they did, and how to tell when their explanations are misleading. My PhD is from the University of Notre Dame (Computer Vision Research Lab, advisor Walter J. Scheirer); my dissertation, Explainable AI for High-Stakes Decision-Making, covers intrinsically interpretable models, the failure modes of post hoc explainers, and defenses against adversarial manipulation of explanations.
At Meta I research and ship interpretability and optimization tooling for production generative AI, and contribute to the open-source Captum library.
Full list on the portfolio page and Google Scholar.