Research Scientist, Atlas Behavior Learning

Are you passionate about using machine learning to drive robot behavior? Curious what you’d be able to accomplish with total access to Boston Dynamics robots? As a Research Scientist 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 (RL) and behavioral cloning (BC) 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:

• Design, train, and deploy state of the art robot learning algorithms to tackle mobile &cz bimanual manipulation tasks

• Contribute to foundation models shaping the future of humanoid robotics

• Train control policies using RL to solve dexterous manipulation tasks

• Distil many different policies using BC and RL with pixel observations

• Deploying and debugging learned policies on Atlas

We are looking for:

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

• Extensive Experience training and deploying RL policies for complex behaviors on real robots or simulated characters

• Excitement for integrating, running, and evaluating their learned policies on the robot

• Has in-depth knowledge about domain randomization to bridge the sim-2-real gap

• Strong foundation in Python and modern ML 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 venues including RSS, CoRL, Science Robotics, ICLR, NeuRIPS

• Familiarity with behavior cloning and has trained a diffusion policy from images

• Prior experience with student-teacher training workflows 

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