Machine Learning Hardware Architect, Google Cloud

Google Cloud is seeking a Machine Learning Hardware Architect to shape the future of AI/ML hardware acceleration. This role focuses on driving cutting-edge TPU (Tensor Processing Unit) technology that powers Google's most demanding AI/ML applications. The position offers an opportunity to work on custom silicon solutions that power Google's TPU and contribute to products used by millions worldwide.

The role involves advancing ML accelerator performance and efficiency through a comprehensive approach spanning compiler interactions, system modeling, power architecture, and host system integration. You'll prototype new hardware features, develop transaction-level models, and optimize accelerator design under power and thermal constraints.

As part of the ML, Systems, & Cloud AI (MSCA) organization, you'll work with specialized teams including XLA compiler, Platforms performance, and system design teams. The role requires expertise in computer architecture, chip design, and machine learning, with a focus on developing innovative solutions for Google's TPU roadmap.

The position offers competitive compensation including base salary, bonus, equity, and benefits. Google prioritizes security, efficiency, and reliability across all operations, from TPU development to global network management. This role is perfect for someone passionate about hardware architecture, machine learning, and pushing the boundaries of AI acceleration technology.

Key responsibilities include creating architectural innovations, evaluating system performance, collaborating across teams, and developing next-generation TPU features. The ideal candidate will have strong experience in computer architecture, software development, and machine learning frameworks, with the ability to drive innovation in hardware/software co-design.