About the job
In this role, you will act as the primary specialist for physics engine internals and dynamics, developing high-fidelity, vectorized simulation environments for robotics locomotion, navigation, and interaction/manipulation. You will collaborate with hardware engineers to validate robot models and partner with research scientists to ensure numerical stability and physical accuracy for Sim2Real transfer. Your work focuses on tuning solvers, optimizing collision dynamics, and performing system identification to enable the training of robust robot control policies for complex, physical interactions.
Responsibilities
Develop and maintain the shared simulation software framework, specifically owning the physics integration, robot state management, and control layers
Develop and optimize parallelized (vectorized) physics environments for high-throughput reinforcement learning (e.g., Isaac Lab, MuJoCo)
Tune physics engine parameters (solvers, friction, restitution) to support complex contact-rich scenarios required for dexterous manipulation and agile locomotion.
Implement and validate complex robot models (URDF/MJCF) involving precise actuator and sensor modeling
Collaborate with robot engineers and scientists to perform System Identification (SysID) to minimize the Sim2Real gap
Qualifications
Minimum
3+ years of non-internship professional software development experience
3+ years of non-intternship design or architecture (design patterns, reliability and scaling) of new and existing systems experience
Bachelor's degree or foreign equivalent in Computer Science, Engineering, Mathematics, or a related field
1+ years Software engineering experience in robotics or physics simulation, with a strong understanding of rigid body dynamics and numerical integration
Experience using standard physics engines (e.g., MuJoCo, PhysX, Bullet, Havok)
Preferred
Master’s degree or PhD in Robotics, Computer Science, Mechanical Engineering, or equivalent preferred
Deep understanding of contact dynamics, collision detection algorithms, and numerical solvers
Experience with robotics system identification (SysID) and model validation against real hardware
Experience with GPU-accelerated simulation frameworks (e.g., Isaac Gym/Lab, Mujoco Warp)
Familiarity with tensor frameworks (e.g., PyTorch, JAX, TensorFlow) for writing vectorized code and interfacing with learning pipelines
A passion for robotics and a desire to build intelligent systems that can positively impact the world.