Sr Applied Scientist - Robotics Simulation, Robotics R&D

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

Job :  |  Services LLC

We are looking for a Senior Applied Scientist to join the Robotics Simulation team at Amazon Robotics. This role combines deep traditional robotics expertise (kinematics, dynamics, control, motion planning) with fluency in modern Physical AI approaches (imitation learning, vision-language-action models, world models, diffusion policies). You will be the technical anchor who bridges the gap between what works in simulation and what works on real robots.

You will mentor junior scientists building RL and imitation learning pipelines, provide hands‑on technical direction on sim‑to‑real transfer, foresee pitfalls in robot learning workflows before they become blockers, and drive the robotics development methodology for the team. This is not a pure research role: you will work directly with real robot hardware, simulation environments, and production deployment pipelines, ensuring that learned policies transfer reliably from GPU-accelerated simulation to physical robots operating in Amazon fulfillment centers.

While this role is expected to engage with the research community and may produce publications, the primary measure of success is deployed robot capability, not paper count. We value scientists who ship.

• Provide technical robotics direction for the team's Physical AI program, spanning simulation environment design, policy training, sim‑to‑real transfer, and real‑world validation across multiple robotics platforms.
• Mentor junior applied scientists and engineers on robot learning best practices, helping them diagnose sim‑to‑real gaps, debug policy failures on hardware, and iterate toward deployable solutions.
• Design and execute sim‑to‑real transfer strategies, including system identification, domain randomization, physics parameter tuning, and visual domain adaptation, drawing on both classical and learned approaches.
• Architect policy training pipelines that combine teleoperation data, synthetic demonstrations, reinforcement learning, and imitation learning (e.g., VLA models, diffusion policies, behavior cloning) for manipulation tasks.
• Lead sim‑to‑real analysis: define metrics and methodologies for evaluating simulation fidelity, identifying where simulation diverges from reality, and prioritizing modeling improvements that impact downstream policy performance.
• Collaborate with hardware teams on robot embodiment modeling, ensuring that digital twins accurately capture kinematics, joint dynamics, actuator limits, contact behavior, and sensor characteristics.
• Evaluate and integrate state‑of‑the‑art approaches from the Physical AI research community (foundation models for robotics, world models, action‑chunking transformers, generalist policies) into the team's simulation and training infrastructure.
• Contribute to end‑effector modeling and physics tuning, ensuring physically plausible contact interactions and accurate tool behavior in simulation across diverse manipulation hardware.
• Drive technical design reviews, author high‑level design documents, and set the scientific direction for simulation fidelity and robot learning initiatives.

The Robotics Simulation team is a ~30‑person multidisciplinary organization of SDEs, Applied Scientists, and Technical Artists at Amazon Robotics. We build the simulation infrastructure that powers Physical AI development, from photorealistic synthetic data to GPU‑accelerated training environments. Our simulation infrastructure enables robots to be designed, trained, and validated entirely in simulation before physical hardware exists, compressing development timelines and de‑risking hardware programs across Amazon Robotics.

The team currently delivers end‑to‑end simulation stacks for Amazon's robotics programs, including high‑fidelity robot digital twins, teleoperation data collection infrastructure, scalable synthetic demonstration generation, VLA/diffusion policy training and inference pipelines, domain randomization for visual…