We are seeking a highly experienced and motivated Principal AI Engineer to join our Stretch Grasping Intelligence team. In this pivotal role, you will be instrumental in guiding the team in building solutions that we can deliver to our customers. You will develop novel AI algorithms to solve real-world mobile perception and manipulation problems. You will pioneer techniques that tightly couple perception to robot behavior and planning and produce efficient and robust policies. You will collaborate closely with software, controls, and hardware teams to rapidly test, iterate, and deploy your algorithms on robot. You will also provide mentorship to other engineers, being a recognized leader that advocates for the right solutions to maximize the capabilities of the Stretch robot.
Our team is responsible for enabling the Stretch robot to understand the environment it operates in, particularly in relation to manipulation tasks in warehouse environments. We also develop and maintain key infrastructure that facilitates the continuous development of these advanced capabilities. Additionally, we regularly conduct on-robot testing and perform in-depth log analysis to continually enhance the performance and reliability of the solutions we offer our customers around the world.
In this role, you will:
Design and build the systems that enable the Stretch robot to perceive the environment so that it can perform manipulation tasks.
Help develop datasets, infrastructure, and tooling to build ML models at scale.
Advocate for and leverage the use of simulation tools (e.g. MuJoCo, Gazebo).
Integrate the use of novel techniques into Stretch software systems.
Collaborate with adjacent teams (e.g. Manipulation, Planning, SW Platform) to define requirements and propose solutions.
Serve as a go-to technical leader on the team, championing AI solutions to tackle challenging problems.
We are looking for:
PhD and 5 years of experience, or MS and 8 years of industry experience in Computer Science, Machine Learning, Robotics, or a related field.
Publications at top tier venues including RSS, CoRL, Science Robotics, ICLR, NeurIPS, CVPR is a plus.
Strong foundation in Python and modern ML frameworks (e.g. PyTorch, Jax).
Prior experience training and deploying AI policies, including working with robot hardware and simulation.
Strong analytical and debug skills.
Experience working with and contributing to large codebases (Python and C++).
Experience with Reinforcement Learning and/or Behavior Cloning is a plus.
Top Skills
What We Do
Boston Dynamics builds advanced mobile manipulation robots with remarkable mobility, dexterity perception and agility. We use sensor-based controls and computation to unlock the potential of complex mechanisms. Our world-class development teams develop prototypes for wild new concepts, do build-test-build engineering and field testing and transform successful designs into robot products. Our goal is to change your idea of what robots can do.
