Rahul Aggarwal is a CVML software engineer with a decade of experience building computer vision and robotics systems, currently working at NVIDIA in Irvine. He combines rigorous academic training (MS in Robotics from UPenn, BS in Computer Science from Georgia Tech) with hands-on research in neural scene representations, disentangled diffusion prediction, and inverse rendering for real-time human pose and shape estimation. Rahul has applied these ideas across industry and lab settings—from improving in-car drowsiness detection and multi-view head pose pipelines to designing SLAM and sensor-fusion stacks for legged robots—demonstrating a knack for turning theoretical latent-space concepts into practical pipelines. He has led teams and projects that emphasize robustness to real-world factors like occlusion, gait dynamics, and lighting, and he’s comfortable across CUDA, multi-sensor integration, and neural scene architectures. Notably, his work focuses on treating perception as a compressed, multiview-consistent latent state that can simplify higher-level planning and control.
10 years of coding experience
3 years of employment as a software developer
Bachelor of Science - BS, Computer Science, 4.00, Bachelor of Science - BS, Computer Science, 4.00 at Georgia Institute of Technology
Master of Science - MS, Robotics, 4.00, Master of Science - MS, Robotics, 4.00 at University of Pennsylvania
Contributions:101 pushes, 1 branch in 3 years 4 months
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.