I am a Postdoctoral Associate in the Interactive Robotics Group at CSAIL and AeroAstro, MIT, working with Prof. Julie Shah. My primary interests lie in AI safety, AI planning, action-model learning, interpretability, analysis of abstractions, and robotics. My research focuses on the safe and reliable behavior of AI agents. I am currently investigating the minimal set of requirements in an AI system that would enable a user to assess and understand the limits of its safe operability. Complementing this work, I also investigate how LLMs can serve as intelligent interfaces that translate between human domain knowledge and automated planning systems, making AI planning accessible to experts across diverse fields.
I obtained a Ph.D. in Computer Science from the School of Computing and Augmented Intelligence at Arizona State University, working with Prof. Siddharth Srivastava. During my Ph.D., I was also affiliated with UC Berkeley’s Center for Human-Compatible Artificial Intelligence, and ASU’s Center for Human, Artificial Intelligence, and Robot Teaming. Prior to that, I completed M.Tech. from the Department of Computer Science & Engineering at IIT Guwahati, advised by Prof. Pradip K. Das. During my master’s, I worked in the areas of bio-inspired robotics, speech processing, and Internet of Things.