Product Engineer, Machine Learning Accelerators, Google Cloud

Google Google · Big Tech · Sunnyvale, CA +1

Product Engineer for Google Cloud's TPU (Tensor Processing Unit) hardware accelerators, focusing on manufacturing, test, and reliability at scale. This role bridges ML accelerator design with global manufacturing, ensuring next-generation AI hardware is manufacturable, testable, and reliable. The engineer will influence hardware design for manufacturability, architect scalable test infrastructure, analyze build data, and drive optimization strategies to maximize factory yield and minimize fallout, directly enabling the expansion of Google's ML services.

What you'd actually do

  1. Own the manufacturing plan and lead reviews between Design and Operations Engineering to drive deliverables that are key to implementing the manufacturing plan, such as DFx and test strategy.
  2. Provide on-site and remote support for pre-production builds. Ensure factory readiness, support manufacturing line bring-up, provide product debug training and gather feedback on build issues.
  3. Lead the technology assessment for new products. Work with the product team to influence design decisions, highlight manufacturing risks, and develop mitigation plans.
  4. Collaborate with Quality and Reliability Engineers to establish NPI and production targets for yield and long-term reliability. Validate product qualification plans, support reliability testing and review results to ensure product performance meets requirements.
  5. Lead cross-functional teams toward resolution of component/build quality excursions during NPI build phases. Manage bonepile and drive yield bridge analysis to improve product quality.

Skills

Required

  • Bachelor's degree in Engineering or equivalent practical experience.
  • 10 years of experience in manufacturing
  • Experience in PCBA (Printed Circuit Board Assembly) and related system.
  • Experience in design for manufacturability and serviceability.

Nice to have

  • Master's degree or PhD in Electrical, Mechanical, Industrial, Materials, or a related engineering field.
  • 12 years of experience in Manufacturing, Quality, or Product Engineering for hardware technology and systems.
  • Experience in technical leadership, project management, and executive communication.
  • Experience working with ODMs, contract manufacturers and component suppliers for data center server accelerator products (GPU, FPGA or ASIC).
  • Experience working with contract manufacturers and suppliers to drive root cause analysis, corrective actions and continuous process improvements
  • Knowledge of SQL queries and scripting in Python or Bash.

What the JD emphasized

  • custom silicon solutions
  • machine learning accelerator design
  • high-volume, high-quality global manufacturing
  • manufacturable, testable, and deeply reliable at scale
  • rapid expansion and peak performance of Google’s ML services
  • technical problem-solving at a global operational scale
  • manufacturing and test engineering
  • influence hardware design for manufacturability, testability, and serviceability (DFx)
  • architect scalable test infrastructure
  • pioneer data-driven optimization strategies to maximize factory yield and eliminate manufacturing fallout
  • optimize capital efficiency, minimize supply chain waste
  • AI and Infrastructure team
  • delivering AI and Infrastructure at unparalleled scale, efficiency, reliability and velocity
  • development of our TPUs
  • Vertex AI for Google Cloud
  • systems research
  • 10 years of experience in manufacturing
  • Experience in PCBA (Printed Circuit Board Assembly) and related system.
  • Experience in design for manufacturability and serviceability.
  • 12 years of experience in Manufacturing, Quality, or Product Engineering for hardware technology and systems.
  • Experience working with ODMs, contract manufacturers and component suppliers for data center server accelerator products (GPU, FPGA or ASIC).
  • Experience working with contract manufacturers and suppliers to drive root cause analysis, corrective actions and continuous process improvements

Other signals

  • TPU Product Engineer
  • machine learning accelerator design
  • high-volume, high-quality global manufacturing
  • scaling the physical infrastructure
  • AI and Infrastructure team
  • AI models
  • hyperscale computing
  • TPUs
  • Vertex AI for Google Cloud