Robotics Simulation Scientist - GPU RL & Sim-to-Real

Amazon Science; Boston (MA); On-site; USD 142,800 - 193,200; Full time

Job summary

Amazon Science is seeking an Applied Scientist for the Robotics Simulation team. The role focuses on designing, building, and validating simulation environments and policy training pipelines to enable robots to learn manipulation and mobility skills in simulation and transfer to real hardware.

You will work at the intersection of robotics simulation science and modern Physical AI, building GPU-accelerated RL environments, implementing imitation learning workflows, and evaluating learned policies

Qualifications

• PhD or Master's degree is required.
• Experience training robot policies using reinforcement learning or imitation learning.
• Experience with physics simulation platforms for robot learning (MuJoCo, Isaac Sim/Lab, PyBullet).
• Knowledge of robotics design, automation systems, and control systems is beneficial.

Responsibilities

• Design and implement GPU-accelerated RL and imitation learning environments in NVIDIA Isaac Lab for manipulation and mobility tasks.
• Build and maintain policy training pipelines and evaluate trained policies in simulation.
• Characterize and reduce sim-to-real gaps through systematic validation against real robot data.
• Implement domain randomization to improve policy robustness and transfer to real hardware.
• Develop sim-to-real transfer techniques including system identification and physics calibration.
• Create robot embodiment validation tests to ensure digital twins match real hardware.

Skills

Reinforcement learning

Imitation learning

Robotics simulation

Policy evaluation

GPU-accelerated simulation

Education

PhD, or Master's degree

Tools

NVIDIA Isaac Lab

MuJoCo

Isaac Sim/Lab

PyBullet

ROS2

URDF/MJCF/USD formats

TensorRT

JAX

PyTorch

Job description

Amazon Science is seeking an Applied Scientist for the Robotics Simulation team. The role focuses on designing, building, and validating simulation environments and policy training pipelines to enable robots to learn manipulation and mobility skills in simulation and transfer to real hardware.

You will work at the intersection of robotics simulation science and modern Physical AI, building GPU-accelerated RL environments, implementing imitation learning workflows, and evaluating learned policies