Generative AI Accelerator Architect and Performance Architect

Be part of a team that pushes boundaries, developing custom silicon solutions that power the future of Google's direct-to-consumer products. You'll contribute to the innovation behind products loved by millions worldwide. Your expertise will shape the next generation of hardware experiences, delivering unparalleled performance, efficiency, and integration.
Google's mission is to organize the world's information and make it universally accessible and useful. Our team combines the best of Google AI, Software, and Hardware to create radically helpful experiences. We research, design, and develop new technologies and hardware to make computing faster, seamless, and more powerful. We aim to make people's lives better through technology.
Individual pay is determined by factors including job-related skills, experience, and relevant education or training.
US: $192000 - $278000 (USD) + 20% bonus target + equity + benefits
Learn more about
benefits at Google
.

Minimum qualifications
Bachelor's degree in Computer Science, Electrical Engineering or a related field, or equivalent practical experience.
10 years of work or academic research experience in computer or chip architecture, performance, or compiler.
Experience with modern Generative AI model architectures (e.g., Large Language Models, Vision Transformers, Image Diffusion Models, etc.).
Experience with one or more general purpose programming languages (e.g., C, C++, or Python) and deep learning frameworks (e.g., TensorFlow, JAX, or PyTorch).

Preferred qualifications
Master's or PhD degree in Computer Science or Electrical Engineering.
Experience in compute IP (NPU/TPU, GPU) development, system PnP modeling and thermal/power analysis.
Experience with design space explorations and hardware/software co-design for machine learning.
Proven track record in driving medium to large scale projects and result delivery.
Excellent communication skills.

Responsibilities
Drive forward-looking GenAI ML architecture exploration for Tensor mobile SoCs while collaborating with research teams, system architecture teams, and compiler engineers to optimize future workloads from both all perspectives across the tech stack including hardware, software, use case, network, and external components.
Work with researchers and Product Manager (PM) teams to define system architecture requirements for future Generative AI use cases.
Apply advanced research in architecture and process technology to get breakthrough power and performance improvements on Generative AI workloads.
Optimize performance of GenAI use cases by defining an optimal model scheduling on the TPU compute engines.