Senior Software Engineer, TPU Supercomputer

Google is seeking a Senior Software Engineer to join their TPU Supercomputer team, focusing on developing and maintaining critical infrastructure for AI computing systems. This role sits at the intersection of distributed systems, hardware, and artificial intelligence, where you'll be responsible for designing and maintaining software for TPU supercomputing systems.

The position requires expertise in system software development with C++ and distributed systems, working within Google's Technical Infrastructure team. You'll be managing the complete lifecycle of both computing and networking components for Google's AI supercomputer/hypercomputers, while creating robust debugging and observability tools.

This is an exceptional opportunity to work with cutting-edge technology in AI infrastructure, collaborating with various specialized teams including Silicon, Software, SRE, and Operations. You'll be directly involved in shaping the future of Google's AI computing capabilities, ensuring reliability and performance across the entire TPU stack.

The ideal candidate should have strong foundations in computer science with at least 5 years of C++ development experience and 3 years in distributed systems. Additional expertise in cloud platforms, machine learning frameworks, and networking technologies would be valuable. This role offers the chance to work on sophisticated technical challenges while contributing to Google's next-generation AI infrastructure.

Working at Google's Taipei office, you'll be part of a global team that takes pride in building and maintaining the architecture that powers Google's extensive product portfolio. The role combines deep technical expertise with collaborative problem-solving, making it perfect for engineers who enjoy working on complex systems at scale.