Applied Scientist II - Robotics Simulation, Amazon Robotics R&D

What you'll do

• Build GPU-accelerated reinforcement and imitation learning environments and train and evaluate robot policies.
• Reduce sim-to-real gaps by validating simulation against real robot data and improving physics, sensors, and robot models.
• Develop domain randomization, transfer methods, and demonstration-data pipelines; collaborate with partner science teams.

What they ask for

• PhD, or Master's degree
• Knowledge of ML frameworks including JAX, PyTorch, vLLM, SGLang, Dynamo, TorchXLA, and TensorRT
• Experience in robotics design, automation systems development, control systems design, or related product development
• 2+ years of experience working with physics simulation platforms for robot learning; experience training and evaluating robot policies using reinforcement or imitation learning; experience with articulated robot simulation and familiarity with sim-to-real transfer concepts

Nice to have

• Hands-on experience deploying learned policies on real robot hardware
• Experience with NVIDIA Isaac Lab/Sim, Omniverse, or USD-based simulation workflows

Pay

171,600.00 - 222,200.00 USD annually (base salary); 142,800.00 - 193,200.00 USD annually (base salary)

Tools

JAX, PyTorch, vLLM, SGLang, Dynamo, TorchXLA, TensorRT, NVIDIA Isaac Lab

AI focus

Physical AI and robot learning: reinforcement and imitation learning, policy training and evaluation, sim-to-real transfer, and learned policies for manipulation and mobility.