Vasanth Sarathy

Principal Research Scientist | Leidos Innovations Center

I study how to make AI systems interpretable, controllable, and grounded in human context. My research explores structured representations and reasoning mechanisms (spanning neurosymbolic models, intent-aware interfaces, and agentic workflows) to bridge the gap between statistical learning and mission-critical decision-making. I’m especially interested in building systems that align with human goals, justify their behavior, and can be trusted to operate in high-stakes environments.

Backround

Previously, I was a Research Assistant Professor of Computer Science at Tufts University, and a Senior Researcher at Smart Information Flow Technologies (SIFT), where I led AI efforts for U.S. defense and intelligence programs. Before entering research, I practiced intellectual property law at Ropes & Gray for nearly a decade.

I hold a dual Ph.D. in Computer Science and Cognitive Science from Tufts University, where I was advised by Matthias Scheutz and Dan Dennett. I also earned an M.S. from MIT, a B.S. from the University of Arkansas, and a J.D. from Boston University School of Law.

This 2023 BU Law article summarizes my journey.

Outside of work, I spend time with my wife, three kids, and other family and friends. When I have some spare time, I write and draw single-panel cartoons, practice shaolin-kempo-karate style martial arts, play chess and design games and visual experiences.

I also run a health and AI podcast called Code and Cure where I discus decoding health in the age of AI with an emergency medicine-trained physician.