Harsh is a postdoctoral fellow at the Vector Institute, collaborating primarily with Gillian Hadfield. His research interests encompass the AI alignment problem, normative infrastructure for intelligent agents, sequential decision-making under uncertainty, and large language models. He obtained his PhD from McGill University in collaboration with Mila, under the supervision of Joelle Pineau, where he focused on alignment challenges in various Reinforcement Learning settings. His doctoral work has been featured in leading machine learning conferences. Additionally, Harsh has industry experience as a software engineer and enjoys contributing to the local startup ecosystem.