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
Strong foundation in Python and modern ML frameworks (e.g., PyTorch and Jax)
In-depth knowledge about domain randomization to bridge the sim-2-real gap
Experience in algorithm design, debugging, and performance optimization
Responsibilities
Design, train, and deploy state-of-the-art robot learning algorithms for mobile and bimanual manipulation tasks
Contribute to foundation models shaping the future of humanoid robotics
Train control policies using reinforcement learning to solve dexterous manipulation tasks
Distill various policies using behavior cloning and reinforcement learning with pixel observations
Deploy and debug learned policies on Atlas robots
Benefits
Direct access to cutting-edge robots and infrastructure for large-scale experiments
Collaborative, mission-driven team where ideas have real impact
Opportunity to help define the future of real-world robotics
Full Job Description
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
The base pay range for this position is between $170,000 to $220,000 annually. Base pay will depend on multiple individualized factors including, but not limited to internal equity, job related knowledge, skills and experience. This range represents a good faith estimate of compensation at the time of posting. Boston Dynamics offers a generous Benefits package including medical, dental vision, 401(k), paid time off and an annual bonus structure. Additional details regarding these benefit plans will be provided if an employee receives an offer for employment.
About Boston Dynamics
Boston Dynamics is an American engineering and robotics design company founded in 1992 as a spin-off from the Massachusetts Institute of Technology. The company is best known for the development of BigDog, a quadruped robot designed for the U.S. military. Boston Dynamics has also developed a number of other robots, including Spot, a four-legged robot designed for indoor and outdoor operation, and Atlas, a humanoid robot designed for a variety of search and rescue tasks. In 2013, the company was acquired by Google X, a subsidiary of Alphabet Inc. In 2020, the company was acquired by Hyundai Motor Group. Boston Dynamics is headquartered in Waltham, Massachusetts.