I'm a researcher in the Autonomous Robotic Manipulation Lab where I'm advised by Tom Power and Prof. Dmitry Berenson. My research focuses on developing efficient inference methods for improving learning-based optimal control and designing intelligent kernels for multimodal, long-horizon robot navigation and manipulation tasks.
Jan 23 - Present
I'm an Instructional Aide (IA) for EECS 497, a capstone course on Human-Centered Software Development and Design. Previously, I led recitation and helped run ROB 101, a course on linear algebra with applications to intelligent systems.
Jun 22 - Aug 22
I interned with Amazon as a research software engineer. There, I built classical and RNN-based demand forecasting models for planning core AWS network capacity and topology. I also improved feature engineering by building efficient data infra & combining various models to achieve a >30% increase.
Jan 22 - Apr 22
I was a software engineer fellow at Academic Innovation (CAI), working on gradecraft, a learning management system. I designed, built and scaled >10 pedagogical features for students, faculty and optimized the grade calculation, release services in Rails by 40%. Wore full-stack, q/a and growth hats.
Sep 21 - Apr 22
I was part of the Strategy division of Michigan Solar Car. There, I worked on infra, constraint optimization and physics simulation models for minimizing race time. I was also involved with V1, where we built a community for ambitious and passionate student builders in Michigan.
Jun 21 - Aug 21
I interned with Quadeye as a quantitative developer. There, I profiled, back-tested, improved stat arb models by 25% and built high-performance Rust backends for trading data lakes.
Past
I grew up in New Delhi, India and graduated from Delhi Public School, R K Puram.
I had the best time of my life learning and building in tech with the people most passionate about it, as part of Exun Clan. I also served on the Student Council, was part of the quizzing and math clubs, and got a Red Tie Award for excellence in CS.
