Research Scientist, Atlas Behavior Learning
Boston Dynamics (company site, opens in a new tab)3+ yrsGujaratOn-siteDirect career pageEst. 35–60 LPA
Posted 4d ago
Reach people at Boston Dynamics
People at this company you can reach
Log in to see who works here
Create a free account or log in to see the people at Boston Dynamics you could write to:
- Recruiters & HR
- People in this function
- Work addresses
Your match
Against your primary resume
Log in to see your match score
Create a free account or log in to unlock your CV match score across:
- Role fit
- Experience
- Industry relevance
Protocol Intelligence
How competitive this role is
Competition
Background fit
Strictness
Log in to see why each signal reads the way it does.
Job description
Structured overview of role & requirements
About This Role
- Design, train, and deploy learning algorithms for mobile and bimanual manipulation, including RL control policies for dexterous tasks.
- Use behavior cloning and RL to distill policies from pixel observations and contribute to robotics foundation models.
- Deploy and debug learned policies on Atlas for real-world use.
Minimum Requirements
- Work Experience Required: MS in Computer Science, Machine Learning, Robotics, or a related field plus 3 years of industry experience, or a PhD in one of these fields or a related field.
- Extensive experience training and deploying RL policies for complex behaviors on real robots or simulated characters.
- In-depth knowledge of domain randomization for sim-to-real transfer.
- Strong Python skills and experience with modern ML frameworks such as PyTorch or JAX.
Ideal Candidate Profile
- Has a PhD or equivalent research experience in reinforcement learning or robotic manipulation, with publications at venues such as RSS, CoRL, Science Robotics, ICLR, or NeurIPS.
- Has trained diffusion policies from images and is familiar with behavior cloning and student-teacher training workflows.
- Has experience integrating, evaluating, and improving learned policies through experiments on physical robots.