Machine Learning Hardware Architect, Google Cloud

Google Cloud is seeking a Machine Learning Hardware Architect to shape the future of AI/ML hardware acceleration, specifically focusing on TPU (Tensor Processing Unit) technology. This role combines advanced computer architecture with machine learning expertise, working on cutting-edge hardware that powers Google's most demanding AI/ML applications.

The position involves developing custom silicon solutions for Google's TPU, requiring expertise in both hardware architecture and machine learning systems. You'll be responsible for advancing ML accelerator performance and efficiency through compiler interactions, system modeling, power architecture, and host system integration. The role includes prototyping new hardware features and developing transaction-level models for performance estimation.

As part of the ML, Systems, & Cloud AI (MSCA) organization, you'll work on technology that impacts billions of users through Google services and Cloud products. The role offers competitive compensation and the opportunity to work with specialized teams on compiler optimization, platforms performance, and system design.

The ideal candidate should have strong experience in computer architecture and hardware design, combined with knowledge of machine learning frameworks like TensorFlow and PyTorch. This position offers the chance to work on next-generation AI hardware while collaborating with various teams across Google's technical infrastructure.

This role represents a unique opportunity to impact the future of AI computing infrastructure while working with some of the most advanced ML hardware systems in the industry. You'll be part of a team that prioritizes security, efficiency, and reliability while pushing the boundaries of hyperscale computing and AI acceleration.