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 sits at the intersection of hardware architecture and machine learning, requiring deep expertise in both domains.
The position 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 offerings. You'll be working on cutting-edge technology that powers Google's most demanding AI/ML applications, including the development of custom silicon solutions for TPUs.
Key responsibilities include creating architectural innovations for Google's TPU roadmap, evaluating system performance metrics, and collaborating across hardware, software, and ML teams. You'll be involved in workload characterization, benchmarking, and developing next-generation TPU features. The role requires a unique blend of hardware architecture knowledge and software development skills, particularly in C++ and Python.
The position offers competitive compensation ($156,000-$229,000 base salary) plus bonus, equity, and benefits. You'll be working in Sunnyvale, CA, alongside teams responsible for Google Cloud's Vertex AI and other leading AI platforms. This is an opportunity to impact the future of hyperscale computing and AI acceleration at one of the world's leading technology companies.
The ideal candidate will have at least 5 years of experience in computer architecture or related fields, with preferred qualifications including an advanced degree and experience with deep learning frameworks like TensorFlow and PyTorch. You'll be working on projects that directly influence Google's AI infrastructure and contribute to products used by millions worldwide.
This role offers the chance to work at the cutting edge of AI hardware development, combining technical expertise with practical implementation in a fast-paced, innovative environment. You'll be part of a team that's pushing the boundaries of what's possible in AI acceleration while maintaining Google's high standards for security, efficiency, and reliability.