The Staff Software Engineer, GPU Performance role at Google focuses on enhancing GPU performance for machine learning models. The position is part of the AI and Infrastructure team, which aims to deliver AI capabilities at scale and efficiency. This role involves working with cutting-edge technology to shape the future of AI and accelerated computing. The engineer will engage with various teams to solve complex performance challenges and drive improvements in GPU architectures.

• Bachelor’s degree or equivalent practical experience.
• 8 years of experience in software development.
• 5 years of experience testing and launching software products.
• 3 years of experience with software design and architecture.
• Experience with modern GPU architectures and performance bottlenecks.
• Experience with low-level GPU programming and performance engineering techniques.

• Identify and maintain LLM training and serving benchmarks to drive performance improvements.
• Engage with teams like DeepMind to address challenging ML model performance issues.
• Run architecture-level simulations on GPU designs and perform roofline analysis.
• Analyze performance metrics to identify bottlenecks and implement solutions.
• Run performance benchmarks on GPU hardware using various internal and external tools.

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