What are the responsibilities and job description for the Research Engineer, Large Behavior Models position at Boston Dynamics?
We are seeking talented software engineers to join our Atlas behavior learning team. You will develop robotics software, applications, tools, and infrastructure as part of our R&D effort teaching Atlas the skills it needs to act in the real world. We are tackling the most challenging problems in humanoid robot manipulation and locomotion through state-of-the-art methods in AI and learning from demonstration. In this project you will develop applications and tools for robot teleoperation, policy evaluation and behavior testing, and data collection to train large behavior models for Atlas. You will work on these hard challenges in close collaboration with roboticists, researcher scientists, DevOps engineers, and data annotation teams. Your contributions will help us build new robot technologies for Atlas and other R&D efforts at Boston Dynamics.
How You Will Make An Impact
How You Will Make An Impact
- Actively participate in ongoing R&D initiatives, collaborating closely with Research Scientists and Infrastructure Engineers
- Work with VR and mocap devices and write code for teleoperation interfaces
- Write software for data logging, data pipelines, training pipelines
- Analyze and track failures in experimental robot runs.
- Develop tools to query and gain insights into data, training, and testing performance metrics
- Work with robot simulation software to develop scenarios, tests, and data collection tools
- Work with annotation teams and develop data annotation tools
- Maintain and improve the code repository, ensuring its ongoing maintenance and improvement to meet evolving needs (CI/CD, testing, deployment)
- 3 years of experience developing software for robotics or related fields
- Advanced knowledge in Python programming, familiarity with C
- Experience with robotics or related problems: 3D transformations, kinematics
- Experience writing GUI tools with Qt
- Experience with ML robotics datasets, robot middleware systems, pubsub, and common sensor modalities
- Experience with cloud infrastructure, storage, databases
- Experience with docker and job orchestration for cloud and on-premise GPU clusters