Software Development Engineer - Robotics Simulation, Robotics R&D

Description

We are looking for a Software Development Engineer to join the Robotics Simulation team at Amazon Robotics. This role sits at the intersection of robotics simulation, physics-based modeling, reinforcement learning infrastructure, and synthetic data generation. You will build the simulation environments, embodiment models, training pipelines, and platform infrastructure that enable Physical AI development for Amazon Robotics programs.

The team delivers end-to-end simulation stacks for robot learning programs, including high-fidelity digital twins of robotic arms and grippers, GPU-accelerated RL training environments using NVIDIA simulation tools, physics tuning and sim-to-real transfer pipelines, and scalable synthetic data generation. Your work will directly impact how robots learn to manipulate objects in Amazon fulfillment centers.

• Design and implement GPU-accelerated reinforcement learning environments using NVIDIA simulation tools, targeting thousands of parallel instances for policy training.

• Build simulation scenes with domain randomization (geometry, mass, friction, lighting, camera placement) to improve sim-to-real transfer.

• Develop physics-based embodiment models and tune simulation parameters to match real-world robot behavior.

• Build distributed RL training infrastructure and data pipelines supporting large-scale policy training across GPU clusters.

• Create config-driven workflows and scripted baselines that allow scientists to use simulation environments without code changes.

• Contribute to the team's synthetic data generation platform and build self-service workflows for downstream ML teams.

• Maintain and upgrade simulation platform dependencies (NVIDIA tools, ROS2, Docker, Python/Ubuntu).

Amazon offers a full range of benefits that support you and eligible family members, including domestic partners and their children. Benefits can vary by location, the number of regularly scheduled hours you work, length of employment, and job status such as seasonal or temporary employment. The benefits that generally apply to regular, full-time employees include:

If you are not sure that every qualification on the list above describes you exactly, we'd still love to hear from you! At Amazon, we value people with unique backgrounds, experiences, and skillsets. If you’re passionate about this role and want to make an impact on a global scale, please apply!

The Robotics Simulation team is a multidisciplinary group 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 RL training environments. Our work directly enables robots to learn manipulation skills in simulation before deploying to real fulfillment centers.

We partner closely with science teams, hardware engineers, and robotics program leads across Amazon Robotics. The team values ownership, technical depth, pragmatic engineering, and a bias for shipping. We work with simulation technologies from NVIDIA and contribute back to the broader robotics simulation community.

• 3+ years of non-internship professional software development experience

• 2+ years of non-internship design or architecture (design patterns, reliability and scaling) of new and existing systems experience

• 3+ years of full software development life cycle, including coding standards, code reviews, source control management, build processes, testing, and operations experience

• Master's or PhD in Robotics, Computer Science, or a related field.

• Hands-on experience with NVIDIA simulation and synthetic data tools.

• Experience building reinforcement learning training environments with domain randomization for sim-to-real transfer.

• Experience modeling contact dynamics for grippers, suction systems, or tendon-driven mechanisms.

• Familiarity with ROS2 and robotics middleware for teleoperation, motion planning, or sensor integration.

• Experience with…