These days I am working on developing multi-modal foundation models for embodied AI, enabling agents to learn to act in both virtual (web) and physical (robotic) environments.
During my PhD, I worked as a full-stack roboticist and developed algorithms that used vision, RL and control for
robust robot manipulation in the real-world.
I also had the wonderful opportunity to intern in Microsoft's RL group where I enjoyed working with Adith Swaminathan. I also spent a great summer in DeepMind's Robotics group working with Jon Scholz and Yusuf Aytar.
Long time ago, I worked as a Game Programmer. I did my undergraduate in Computer Science from IIIT-H.
