Research Engineer, Atlas Physics Simulation for RL

Location: Waltham Office (POST)

Time Type: Full time

Job Description

Are you passionate about using physics simulation, reinforcement learning and humanoid robots? Curious what you’d be able to accomplish with total access to Boston Dynamics robots? As a Research Engineer working on physics simulation on the Atlas Behavior Learning team, you will join a world-class team of engineers and scientists focused on creating groundbreaking mobile manipulation behaviors for humanoids. 

We are investing in reinforcement learning and physics simulation as a key technology for achieving dexterous and robust whole-body manipulation that can be deployed in real-world environments. 

In this role, you will be responsible for:

• Develop large scale physics simulation that can efficiently train reinforcement learning agents

• Evaluate and benchmark different physics simulators, mesh representations and rendering pipelines

• Scale physics simulations to generate millions of samples per second

• Build synthetic rendering pipelines to create photorealistic images

• Extend existing physics simulators to improve simulation quality

We are looking for:

• MS with 3 years of industry experience or PhD in Computer Science, Machine Learning, Robotics, or a related field

• Detailed understanding physics simulation including contact solvers and mesh representations

• Extensive experience with physics simulation including MuJoCo, IsaacSim and Warp

• Experience with rendering pipelines to create photorealistic synthetic images

• Strong foundation in Python, C++ and modern numerical frameworks  (e.g., PyTorch and Jax)

• Experience in algorithm design, debugging, and performance optimization

The ideal candidate has: 

• A PhD or equivalent research experience in reinforcement learning or robotic manipulation

• Publications at top tier robotics venues including RSS, CoRL, Science Robotics, ICRA

• Experience training RL policies in simulation for robots or simulated characters

• Strong understanding of the advantages and disadvantages of gpu based simulators

• Understanding of GPU and CPU compute architectures

• Experience with heterogeneous compute clusters, kubernetes and docker

Why join us? 

• Direct access to cutting-edge robots and the infrastructure to run large-scale experiments

• A collaborative, mission-driven team where your ideas have real impact

• The chance to help define what’s possible in real-world robotics

#LI-JM1