Top expert inReal-Time 3D Graphics and Game Engine Development
Erwin Coumans is a distinguished engineer with 15+ years building foundational physics and simulation technology for games, visual effects, robotics, and machine learning, currently leading Omniverse & Simulation Technology at NVIDIA. He is the creator and long-time lead architect of the widely used open-source Bullet Physics SDK and author of the Tiny Differentiable Simulator, work that bridges real-time engines and differentiable reinforcement learning. At Google Brain he founded the Quadruped Locomotion team and led PyBullet and motion_imitation efforts that advanced sim-to-real robotic learning. His background spans high-performance CPU/GPU optimization, parallelization, and novel numerical solvers—skills proven at AMD, Sony, and in film and game studios adopting Bullet. Comfortable at the intersection of research and production, he routinely mentors students and integrates academic advances into robust engineering. A less obvious strength is his consistent focus on developer ergonomics—Python bindings, pip installs, and visualization tooling—making advanced simulators accessible to practitioners.
Bullet Physics SDK: real-time collision detection and multi-physics simulation for VR, games, visual effects, robotics, machine learning etc.
Role in this project:
Backend Developer
Contributions:23 releases, 8 reviews, 3244 commits in 9 years 8 months
Contributions summary:Erwin primarily contributed to the core physics engine by addressing bugs related to inverse dynamics and implementing new features. Their work included bug fixes in multi-body dynamics, adding a class method to retrieve frame data. They also added improvements for the creation of heightfield terrain and added joint limits to spherical joints.
Tiny Differentiable Simulator is a header-only C++ physics library with zero dependencies.
Contributions:4 commits, 137 pushes, 4 branches in 23 days
physicsdependenciescppdifferentiablezero
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.