Boston Dynamics is developing advanced humanoid robots and needs a Principal Fleet Performance & Reliability Engineer to serve as the critical link between the Controls software team and the Prototype Operations team, independently solving the fleet's toughest problems and improving robot reliability.
Requirements
- Deep familiarity with C++ and Python for on-robot development, debugging, and large-scale data analysis.
- Expert-level knowledge of electric brushless DC motor functionality and motor control firmware.
- A deep understanding of robotics fundamentals and extensive experience working with complex robot data (e.g., sensor data, joint states).
- Experience architecting and implementing large-scale data pipelines and working with time-series databases.
- Experience leading the design and development of data visualization dashboards and tools for complex systems.
- Deep expertise in statistical analysis and signal processing.
- Prior experience in a role focused on robotics reliability, diagnostics, or fleet management for a complex hardware product.
Responsibilities
- Serve as the primary controls engineering point of contact for the Prototype Operations team, providing expert, hands-on support for robot bring-up, diagnostics, and repair.
- Independently own and conduct deep-dive investigations into the most critical and ambiguous fleet-wide issues, spanning the full stack from low-level motor firmware to high-level robot operations.
- Drive the continuous improvement of the our automated diagnostic system and other data analysis tools, focusing on increasing the speed and accuracy of troubleshooting for technicians.
- Develop and document best practices for diagnosing and resolving common issues, creating resources and tools that empower the operations team to solve more problems autonomously.
- Synthesize findings from fleet data and repair operations to provide direct, data-driven feedback to the broader hardware and software design teams, influencing future designs.
- Mentor other engineers in best practices for debugging, system analysis, and designing for reliability.
Other
- A proven ability to work hands-on with complex hardware and collaborate effectively with technician and operations teams in a manufacturing or lab environment.
