TPU Validation Manager

Google•Mountain View, CA

17h•$192,000 - $278,000

About The Position

Be part of a team developing custom silicon solutions that power Google's direct-to-consumer products. The team brings together Google AI, Software, and Hardware to research, design, and develop technologies and hardware that make computing faster, seamless, and more powerful, with the aim of improving people's lives through technology. This role leads silicon validation for Google's Tensor Processing Unit (TPU), a custom machine learning accelerator used in mobile SoC products. Individual pay is determined by job-related skills, experience, and relevant education or training. The US salary range is $192,000–$278,000, plus a 20% bonus target, equity, and benefits.

Requirements

Bachelor's degree in Electrical Engineering, Computer Engineering, Computer Science, or a related field, or equivalent practical experience.
8 years of experience in SoC validation.
5 years of experience in people management and developing employees.
Experience with ML accelerator and Mobile SoC architecture.

Nice To Haves

Master's degree or PhD in Electrical Engineering, Computer Engineering, or Computer Science, with an emphasis on computer architecture.
Experience leading or managing ML accelerator verification teams.
Experience with pre-silicon validation on emulation platforms.
Experience with system-level and board-level debug.

Responsibilities

Lead and manage the team responsible for silicon validation of the Tensor Processing Unit (TPU) in mobile SoC products.
Drive the development of test plans and advanced verification frameworks for pre-silicon emulation and post-silicon validation.
Oversee power and performance measurement and ensure correlation with pre-silicon results to meet product goals.
Collaborate with Architecture, Design, Software, and Design Verification (DV) teams to resolve technical issues and support silicon debug throughout the product life cycle.
Ensure the team meets project schedules and provides excellent support for internal customers and field failure analysis.