The Staff Software Engineer, TPU, Performance role at Google focuses on optimizing machine learning models for Tensor Processing Units (TPUs). The position is part of the Core Machine Learning organization, which is responsible for pioneering work in ML infrastructure and performance. Engineers in this role will work on Gemini and open-source models, improving performance for large-scale ML workloads. The team aims to influence next-generation TPU architectures and enhance the technical foundation behind Google's flagship products.

• Bachelor’s degree or equivalent practical experience.
• 8 years of experience in software development.
• 5 years of experience with speech/audio technology, reinforcement learning, ML infrastructure, or another ML field.
• 5 years of experience with ML design and infrastructure, including model deployment and evaluation.
• 5 years of experience testing and launching software products, and 3 years of experience with software design and architecture.

• Identify and maintain ML training and serving benchmarks that represent Google production and the broader ML industry.
• Achieve performance for customer launches and benchmark submissions for third-party and open-source models.
• Use benchmarks to identify performance opportunities and improve the compiler and runtime in collaboration with relevant teams.
• Engage with Google Product teams and researchers to solve performance problems and onboard new ML models on TPU hardware.
• Analyze performance and efficiency metrics to identify bottlenecks and design solutions at a fleet-wide scale.

• Employees at Google are often offered benefits like comprehensive health insurance, 401(k) matching, and flexible work arrangements, among other benefits.