Boston Dynamics is developing intelligent robots for complex, human-centric environments. A critical component is creating a rich, accurate, and real-time understanding of the world around the robot, which serves as the foundation for Reinforcement Learning (RL) policies. The job is to build the bridge between the robot's perception of the world and its ability to act within it.
Requirements
- Direct experience with Reinforcement Learning and a solid understanding of other machine learning techniques.
- Strong proficiency in C++ and Python.
- Experience with 3D geometry, transformations, and data structures.
- A solid understanding of robotics fundamentals, including kinematics and coordinate frames.
- Familiarity with simulation environments (e.g., Isaac Sim, MuJoCo).
- Experience working with large-scale 3D data from sensors such as cameras and LiDAR.
- Familiarity with modern software development practices, including version control, testing, and CI/CD.
Responsibilities
- Design, build, and maintain the software interfaces that connect our robot's real-time 3D world model to our RL-based control systems.
- Develop and optimize the data pipelines that provide our RL policies with the necessary environmental information to make intelligent decisions.
- Collaborate with our perception and controls teams to ensure that the environmental model is accurate, efficient, and tailored to the needs of our learning algorithms.
- Implement and test new features that enable our robots to better understand and interact with their surroundings.
Other
- A Bachelor's degree in Computer Science, Robotics, or a related field with 4+ years of professional experience, or a Master's degree with 2+ years of experience.
- A passion for building robust and reliable software for real-world robotic systems.
