I am a research scientist at Robert Bosch LLC, Sunnyvale, USA, where I develop machine learning and computer vision methods for problems in autonomous driving, and industrial manufacturing.

Academically, I am interested in model interpretability, data-centric machine learning, and more broadly, the “science” of deep learning, i.e., understanding mechanisms driving model behaviour. For more information, please see my research themes and publications.

I was previously a postdoctoral research fellow with Hima Lakkaraju at Harvard University. I completed my PhD with François Fleuret, at Idiap Research Institute & EPFL, Switzerland.

I am an organizer on:

• the theory of interpretable AI online seminar series, where we bring in interesting guests to talk about advances in the theory of interpretability
• XAI in Action: Past, Present and Future workshop at NeurIPS 2023, where we focussed on the practical applications of explainable AI
• Interpretable AI: Past, Present and Future workshop at NeurIPS 2024, where we focussed on interpretability for large-scale AI models

I also helped teach an explainable AI course at Harvard during spring 2023.

Note: If you are a student looking for mentorship / collaboration in the area of interpretable or explainable AI, feel free to reach out!