System Hardware Reliability Engineer — Predictive PHM + ML

Google Inc.; Sunnyvale (CA); On-site; USD 188,000 - 274,000; Full time

Job summary

Google Sunnyvale is hiring a System Hardware Reliability Engineer to own physics-based health management and predictive analytics for high-density compute hardware. You will define reliability standards, design tests, and oversee analysis while collaborating with product and design teams.

The role emphasizes physics-of-failure modeling integrated with ML, forecasting remaining useful life and optimizing cooling and power strategies across the global fleet.

Qualifications

• Bachelor’s degree in Reliability Engineering or related field.
• 8+ years applying Design for Reliability in consumer electronics.
• 8+ years hardware reliability engineering and predictive analytics.

Responsibilities

• Define standards, specify tests, and supervise execution and failure analysis.
• Develop PHM models and physics-informed ML for reliability forecasting.
• Lead risk-benefit trade-offs between cooling, capacity, and lifespan.

Skills

Design for Reliability

Hardware reliability engineering

Predictive analytics

Physics-informed ML

Education

Bachelor's degree (Reliability Engineering)

Master's degree (Reliability Engineering)

Tools

PyTorch

TensorFlow

PoF modeling

Job description

Google Sunnyvale is hiring a System Hardware Reliability Engineer to own physics-based health management and predictive analytics for high-density compute hardware. You will define reliability standards, design tests, and oversee analysis while collaborating with product and design teams.

The role emphasizes physics-of-failure modeling integrated with ML, forecasting remaining useful life and optimizing cooling and power strategies across the global fleet.