At Boston Dynamics, we are developing the next generation of intelligent robots capable of operating in complex, human-centric environments. A critical component of this effort is creating robust, dynamic, and intelligent behaviors through advanced machine learning. We are seeking a talented Robotics Engineer to join our Atlas Controls team and help pioneer new methods in reinforcement learning for complex robotic systems.
As a Senior Robotics Research Engineer, you will be a key contributor to solving one of the most challenging problems in robotics: teaching a humanoid robot to perform complex locomotion and manipulation tasks. Your work will focus on implementing, testing, and refining reinforcement learning policies to create sophisticated and robust behaviors. This is a unique opportunity to help translate cutting-edge research into real-world capabilities on one of the world's most advanced robots.
What You'll Do:
Implement, train, and test reinforcement learning algorithms to create robust and dynamic locomotion and manipulation behaviors.
Leverage high-fidelity simulation environments to develop, validate, and debug control policies.
Assist in analyzing the performance of policies on the physical robot and work on sim-to-real challenges.
Collaborate with controls, perception, and software teams to integrate your work into the broader robot software stack.
We're Looking For:
Master's degree in Robotics, CS, or a related field; OR a Bachelor's degree with 2+ years of hands-on professional experience in a related area.
Hands-on experience developing and implementing learning algorithms for control tasks (can include significant academic, internship, or professional projects).
Experience with physics simulation engines (e.g., MuJoCo, Isaac Sim)
Proficiency in Python and familiarity with C++.
A solid understanding of robotics fundamentals, including kinematics, dynamics, and coordinate frames.
Nice-to-have:
Demonstrated experience with projects involving physical robotic systems.
Experience integrating perceptual data (e.g., vision, depth) into a control policy.
A passion for building robust and reliable software for real-world robotic systems.
Publication record in top-tier robotics, machine learning, or computer vision conferences (e.g., CoRL, RSS, ICRA, CVPR, NeurIPS).