I recently joined United Technologies Research Center at Berkeley. Earlier, I was a postdoctoral researcher in EECS at UC Berkeley, working with Prof. Stuart Russell. My research is on principles and applications of sequential decision making and reasoning under uncertainty. This involves the mathematical and computational aspects of designing safe intelligent systems that can work effectively for, and with, humans. With this objective, I am particularly interested in the formal foundations and computational techniques for using abstractions to enable efficient hierarchical reasoning in autonomous agents that work in the real world.