Member of Technical Staff, Microsoft Robotics (robotics Simulation)

Microsoft Microsoft · Big Tech · Redmond, WA +1 · Software Engineering

This role focuses on designing, developing, and optimizing physics-based simulation frameworks for robotics applications. It involves creating high-fidelity simulation environments for robot kinematics, dynamics, sensors, and actuators, enabling reinforcement learning training, closed-loop policy evaluation, synthetic data generation, and sim-to-real transfer. The role bridges advanced physics simulation, robotics autonomy, and ML infrastructure to accelerate the development and deployment of physically grounded AI.

What you'd actually do

  1. Design, develop, and maintain physics-based simulation frameworks for robotics applications, including accurate modeling of rigid-body dynamics, articulated mechanisms, contact and friction, deformable objects, and fluid interactions as required by target robot platforms.
  2. Implement essential robotics simulation features, including accurate sensor models (cameras, LiDAR, IMUs, force/torque sensors, tactile arrays), actuator models, controller interfaces, and communication protocols that mirror real robot hardware behavior.
  3. Build real-to-sim and sim-to-real workflows for dynamic environments and robotics tasks, implementing domain randomization, system identification, and physics parameter tuning to minimize sim-to-real gaps.
  4. Develop simulation infrastructure for robot learning policies, including reinforcement learning training at scale, with parallelized environment instances, reward instrumentation, curriculum management, and integration with distributed ML training frameworks.
  5. Collaborate closely with robotics engineers, ML researchers, and platform engineers to enable large-scale robotics development, training pipelines, benchmarking suites, and automated evaluation workflows.

Skills

Required

  • C++
  • Python
  • physics simulation engineering
  • robotics
  • ML infrastructure

Nice to have

  • C#
  • Java
  • JavaScript
  • Master's Degree
  • MuJoCo
  • Isaac Sim
  • Gazebo
  • Genesis
  • USD
  • URDF
  • MJCF
  • SDF
  • domain randomization
  • system identification
  • physical world models

What the JD emphasized

  • physics-based simulation frameworks
  • reinforcement learning training
  • sim-to-real transfer
  • robot learning policies

Other signals

  • physics-based simulation frameworks
  • robotics AI models
  • physically grounded agentic AI workflows
  • reinforcement learning training
  • sim-to-real transfer