Staff Software Engineer, GPU Performance, Core ML

Google is seeking a Staff Software Engineer to join their Core Machine Learning organization, focusing on GPU performance optimization. This role is at the forefront of Google's initiative to expand its GPU expertise, working on transformative solutions that will shape the future of AI and accelerated computing. The position combines deep technical expertise in GPU architecture, machine learning infrastructure, and performance optimization with technical leadership responsibilities.

The role is part of the ML, Systems, & Cloud AI (MSCA) organization, which is responsible for the hardware, software, and infrastructure powering Google's services and Cloud AI offerings. The successful candidate will work on optimizing the entire GPU software stack, from model design to low-level kernels, directly impacting billions of users worldwide through Google's products and cloud services.

Key responsibilities include optimizing benchmarks and critical systems, developing groundbreaking optimization techniques, and collaborating with experts across different domains. The position requires extensive experience in software development, machine learning infrastructure, and GPU technologies, making it ideal for someone who combines technical depth with leadership capabilities.

This role offers unique opportunities to work with cutting-edge GPU technology, access to Google's extensive resources and tooling, and the chance to influence the direction of machine learning infrastructure at scale. The position is based in London, UK, offering the opportunity to work with a global team of experts in machine learning, compiler design, and systems architecture.