Back to jobs
Job Description
- Drive the technical roadmap across a various hardware, data center, and cloud infrastructure portfolio while leading next-generation TPU product introductions.
- Set and communicate team priorities, support the organization's goals and develop the mid-term technical goal and roadmap. Align strategy, processes, and decision-making across teams.
- Develop, test, and help deploy and debug the lower level software for TPU systems including firmware, driver, user space libraries, Linux Kernel, power, thermal, and test development.
- Design and implement superpod software to control and manage TPU AI hypercomputers containing thousands of TPU machines, constructing and connecting TPU slices with shape requested by users.
- Build and evolve the TPU hypercomputer health ecosystem, integrating hardware and networking quality assurance, repair, and monitoring. Partner with cross-functional infrastructure, engineering, and external teams to plan and execute end-to-end programs, from product development to productivity gains. .