Senior Applied Scientist, Amazon Industrial Robotics
Core
Develop high-performance simulation modeling and tools for rigid and deformable body simulation to support real-time and batch workflows for advanced robotics systems.
Role type
Senior Applied Scientist (Robotics Simulation)
Builds
Scalable simulation solutions and validation pipelines for robotic dexterous manipulation and locomotion
Domain
Robotics, Physics-based Simulation, Numerical Methods
Deliverable
production ML models | infrastructure
Required skills
Python, C++, CUDA, numerical methods for multibody dynamics, frictional contact, Finite Element Method (FEM), Material Point Method (MPM), linear algebra, differential equations, GPU programming
Preferred skills
Java, bimanual manipulation, imitation learning, reinforcement learning for locomotion, teleoperation systems
Technologies
MuJoCo, Newton, Drake, Isaac Lab, CUDA, Warp
Responsibilities
Translate physical modeling needs into robust simulation solutions; Design and implement high-performance simulation modeling and tools; Identify and optimize performance bottlenecks in simulation pipelines; Build validation and unit testing pipelines to ensure correctness and physical fidelity; Identify potential sources of sim-to-real gaps and propose modeling approximations; Stay current with advances in numerical methods, parallel computing, and GPU architectures
Seniority
Senior, hands-on IC
