Staff TPU Performance Engineer – ML Compiler Optimizations

Google Inc.; Sunnyvale (CA); On-site; USD 207,000 - 300,000; Full time

Job summary

Google is seeking a Staff Software Engineer, TPU, Performance in Sunnyvale, CA to drive optimization of TPU architectures and Gemini ML workloads. You will own performance targets, partner with ML researchers, and influence compiler/runtime choices across teams.

The role requires deep ML systems expertise and a proven track record delivering scalable software on accelerator hardware, within Google's inclusive engineering culture.

Qualifications

• Bachelor’s degree or equivalent practical experience.
• 8 years of software development experience.
• 5 years of experience with one or more: speech/audio, reinforcement learning, ML infrastructure, or ML field specialization.
• 5 years of experience with ML design and ML infrastructure (model deployment/evaluation, data processing, debugging, fine tuning).
• 5 years of experience testing, and launching software products, and 3 years of experience with software design and architecture.

Responsibilities

• Identify and maintain ML training and serving benchmarks that are representative to Google production and broader ML industry.
• Achieve performance for customer launches, and for third-party/Open-Source Software models.
• Use benchmarks to identify performance opportunities and drive out-of-the-box performance toward improving the compiler/runtime.
• Engage with Google Product teams and researchers to solve performance problems and enable large-scale ML workloads.
• Analyze performance and efficiency metrics to identify bottlenecks, design and implement solutions at fleet-wide scale.
• Represent Google’s Core ML commitments and help guide cross-team technical decisions.

Skills

Software development

ML/AI knowledge

Communication

Education

Bachelor’s degree or equivalent practical experience

Job description

Google is seeking a Staff Software Engineer, TPU, Performance in Sunnyvale, CA to drive optimization of TPU architectures and Gemini ML workloads. You will own performance targets, partner with ML researchers, and influence compiler/runtime choices across teams.

The role requires deep ML systems expertise and a proven track record delivering scalable software on accelerator hardware, within Google's inclusive engineering culture.