The Staff Software Engineer, TPU Performance role at Google focuses on optimizing the efficiency of Tensor Processing Units (TPUs) and enhancing machine learning (ML) training and serving benchmarks. The position is part of the AI and Infrastructure team, which is dedicated to delivering AI capabilities at scale and improving performance across Google's production and research workloads. Engineers in this role will collaborate with product teams and researchers to solve complex performance challenges and drive innovations in ML model training. This position requires a blend of technical expertise and leadership skills to manage project priorities and deliver impactful solutions.

• Bachelor's degree or equivalent practical experience.
• 8 years of experience in software development.
• 5 years of experience testing and launching software products.
• 5 years of experience with performance, large-scale systems data analysis, visualization tools, or debugging.
• 3 years of experience with software design and architecture.
• Experience with ML performance analysis and benchmarking.

• Focus on Tensor Processing Unit (TPU) fleet efficiency analysis and performance optimization.
• Identify and maintain Machine Learning (ML) training and serving benchmarks.
• Collaborate with Google product teams and researchers to solve performance problems.
• Analyze performance and efficiency metrics to identify bottlenecks and design solutions.
• Explore model and data efficiency techniques such as model co-design, quantization, and sparsity.

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