Physical Intelligence is bringing general-purpose AI into the physical world. We are a team of engineers, scientists, roboticists, and company builders developing foundation models and learning algorithms to power the robots of today and the physically-actuated devices of the future.
The team
This role is part of the Runtime team, but will include deep collaboration with the Research, Hardware, and Fleet teams.
In this role you will:
Drive the architecture and implementation of embedded firmware for devices crucial to PI’s data collection goals
Work with hardware and software teams to ensure the new devices we are building work seamlessly with existing and future data pipelines
Embedded Linux System Bring-up: Lead the integration of embedded Linux devices with real-time sensor processing. This includes developing drivers for high-speed sensors, BSP development and customization, kernel configuration and debugging, hardware bring-up, and performance tuning across the hardware/software boundary.
Hardware/Software Debugging: Use hardware abstraction tools and laboratory equipment to identify and resolve complex timing issues, race conditions, and hardware-software interface bugs.
Power Optimization: Analyze and reduce power consumption for battery-operated devices, including on radio sleep states and sensor low-power modes.
What we hope you'll bring:
BS/MS in Computer Science, Electrical Engineering, or related field.
Strong software engineering and infrastructure skills, including building data pipelines, evaluation frameworks, and tools for rapid iteration.
Comfort working hands-on with hardware.
Strong communication skills for collaborating with hardware, software, and research teams
Demonstrated experience leading initiatives from concept to production on aggressive schedules, and turning ambiguous product goals into functional requirements
Experience leading initial board bring-up and software design for first-of-their-kind embedded devices.
Hands-on experience with SPI, I2C, UART, USB, and the ability to debug complex hardware-software interactions.
Experience architecting, implementing and debugging concurrent and multithreaded firmware services
Deep understanding of modern operating systems, computer architecture, and trade-offs between compute, memory, and storage.
Experience bringing up and integrating sensors on embedded systems; camera system bring-up, integration, and tuning is a plus.
Proficiency in C++
Familiarity with Bash scripting and Python for tooling and automation.
Bonus points if you have:
Nice to have: Direct experience with Linux Kernel development, including writing or debugging drivers, managing device trees, or optimizing kernel-space performance.
Pursuant to the San Francisco Fair Chance Ordinance, we will consider for employment qualified applicants with arrest and conviction records.