Hi! I'm a Machine Learning Engineer at Vijil, where I work on building tools to evaluate and improve the trustworthiness of AI agents and large language models.
I completed my M.S. in Computer Science & Engineering at the University of Michigan, Ann Arbor, where I was a research assistant at the University of Michigan Transportation Research Institute (UMTRI) and a Graduate Student Instructor for the Department of Computer Science and Engineerng. Prior to Michigan, I worked as a Software Engineer at Microsoft where I worked on improving the quality of Bing's search index, and even further back, I interned at Intel where I researched few-shot object detection.
My interests broadly span safe & trustworthy ML, governance of AI systems, uncertainty quantification, and data-efficient learning.
Building evaluation and guardrail systems for AI agents.
Developed computer vision models to determine vehicle occupant posture using LiDAR and IR data.
Built automated techniques to reduce junk and spam in Bing's search index.
Created a novel architecture for few-shot incremental object detection, achieving state-of-the-art performance on the India Driving Dataset.
* indicates joint first author
Loading publications…
Graduate Student Instructor at the University of Michigan:
Fall 2023 (341 students) · Fall 2022 (274 students)
Winter 2024 (80 students) · Winter 2023 (73 students)