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

Amazon Amazon · Big Tech · Westboro, MA · Data Science

Senior Applied Scientist role focused on developing 3D physics-based simulation environments and tools for robotics, specifically for training large-scale machine learning models using reinforcement learning and synthetic data generation. The role involves establishing processes, building real-to-sim workflows, and minimizing sim-to-real gaps, with a secondary focus on enabling agentic systems through simulation.

What you'd actually do

  1. Mentor a team of scientists on Robotic Simulation best practices
  2. Establish processes for developing simulations for reinforcement learning, closed-loop simulations and synthetic data generation
  3. Create frameworks for incorporating essential robotics features, including accurate modeling of sensors, actuators, and controllers into simulations
  4. Build real-to-sim workflows for dynamic environments and robotics tasks
  5. Direct the implementation of simulation features to minimize sim-to-real gaps through domain randomization and system identification

Skills

Required

  • PhD, or Master's degree and 6+ years of applied research experience
  • Experience programming in Java, C++, Python or related language
  • Experience with neural deep learning methods and machine learning

Nice to have

  • Broad experience across a range of physics simulators (IsaacSim, IssacLab, MuJoCo, Drake, etc.), both as a sim “power-user” and technical developer
  • First-hand experience in sim2real transfer (i.e. developing learned policies in sim and successfully getting them to work on real robots)
  • Experiencing in closing sim2real gaps both in terms of visual fidelity and physics fidelity
  • Deep expertise in robotics (controls, motion planning, perception, etc.), ideally both in the context of manipulation and locomotion
  • Deep expertise in reinforcement learning, especially in the context of robotics
  • Experience with VLAs and using simulation for data generation and benchmarking
  • Experience with ROS2

What the JD emphasized

  • lead the development
  • automate reusable sim asset creation
  • training large-scale machine learning models
  • reinforcement learning
  • synthetic data generation
  • real-to-sim workflows
  • minimize sim-to-real gaps

Other signals

  • leading development of simulation environments
  • automating reusable sim asset creation for training large-scale machine learning models
  • establishing processes for developing simulations for reinforcement learning
  • building real-to-sim workflows
  • minimizing sim-to-real gaps