Prior to joining UCSD, I was senior deep learning engineer at Akasha Imaging (acquired by Intrinsic.ai, an Alphabet company).
At Akasha, I worked on developing a Multiview 6DOF Pose estimation system for industrial automation. I also played a lot of Ping Pong with Agastya Kalra.
Internships: In the past, I had the opportunity to spend two summers, in 2018 and 2020, at NVIDIA, developing and optimizing CUDA kernels.
Some of this work is now a part of CUTLASS and NVIDIA RAPIDS. I was at Qualcomm AI in 2023, working on memory efficient dynamic human reconstruction that resulted in a US Patent. I spent the summer of 2025 at Amazon Lab126, training multi-modal LLMs for home layout estimation from 3D point clouds as inputs. I am currently seeking research internship opportunities starting in Summer or Fall 2026.
I am broadly interested in 3D vision, graphics, and computational imaging. My current research focuses on 3D scene representations
(NeRFs, 3D Gaussian splatting, etc.), diffusion models and their applications in computational imaging inverse problems.
I also work on 3D vision/perception and 6-DoF pose estimation for ocean floor inspection.
GuruKrupa Fellowship at UCLA
South East Asia ML Summer School (SEAMLS) -- top 100 out of 1100 applicants.
Silver medalist at IJSO 2013, representing the Indian team.