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

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

Benefits offered by this job

RSUs

Sign-on bonus

Job summary

Amazon Robotics is hiring an Applied Scientist II for Robotics Simulation in Boston. You will design GPU-accelerated RL environments, build policy training pipelines, and validate simulations against real hardware.

You will drive sim-to-real transfer research, implement domain randomization, and validate end-effector interactions to accelerate robotics development. You will lead end-to-end simulation deliverables, collaborate with SDEs, Technical Artists, and partner science teams, and

Qualifications

• PhD or Master’s degree in a relevant field.
• Proficiency with ML frameworks (JAX, PyTorch, vLLM, SGLang, Dynamo, TorchXLA, TensorRT).
• 2+ years with physics simulation platforms for robot learning (MuJoCo, Isaac Sim/Lab, PyBullet, Drake).
• Experience training robot policies with RL or imitation learning and evaluating in simulation.
• Experience with articulated robot simulation (URDF/MJCF/USD).
• Familiarity with sim-to-real transfer concepts (domain randomization, system identification, physics calibration).

Responsibilities

• Design and implement GPU-accelerated RL and imitation learning environments for manipulation and mobility tasks.
• Build and maintain policy training pipelines for diverse model architectures and evaluate in simulation.
• Characterize and reduce sim-to-real gaps using simulated vs real robot data, implement improvements.
• Apply 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 fidelity to hardware.
• Build data pipelines for recording, replaying, and augmenting demonstration data.
• Contribute to end-effector modeling and contact dynamics tuning in simulation.
• Author design documents and participate in technical reviews.
• Collaborate with partner science teams to align with training requirements.

Skills

ML frameworks: JAX, PyTorch, TensorRT

Reinforcement learning

Imitation learning

Robotics simulation

URDF/MJCF/USD familiarity

Sim-to-real transfer

Education

PhD or Master’s degree

Tools

MuJoCo

Isaac Sim/Lab

PyBullet

Drake

Job description

Amazon Robotics is hiring an Applied Scientist II for Robotics Simulation in Boston. You will design GPU-accelerated RL environments, build policy training pipelines, and validate simulations against real hardware.

You will drive sim-to-real transfer research, implement domain randomization, and validate end-effector interactions to accelerate robotics development. You will lead end-to-end simulation deliverables, collaborate with SDEs, Technical Artists, and partner science teams, and