About Me

I am a Staff Machine Learning Scientist at Visa, working on transformer-based and foundation-model systems for high-throughput production decisioning. I received my PhD in Computer Science from the University of California, Davis, advised by Prof. Kwan-Liu Ma.

My work focuses on model evaluation, AI reliability, and human-centered analysis of deep learning systems. I am interested in understanding how foundation models behave, where they fail, and how to make their behavior more reliable and actionable in production settings. My research spans LLM/VLM evaluation, transformer attention analysis, adversarial vulnerability diagnosis, SHAP-based model explanation, and simulation decision support.

Current interests: foundation-model evaluation, LLM/VLM reliability, model behavior analysis, human-in-the-loop evaluation, responsible AI, and production ML systems.

Checkout my publication page and my Google Scholar for the latest projects!