Senior Tensor Processing Unit Architect, Silicon
Description For Senior Tensor Processing Unit Architect, Silicon
Join Google's CoreIP Hardware Architecture team as a Senior Tensor Processing Unit Architect, where you'll be at the forefront of developing custom silicon solutions that power Google's direct-to-consumer products. This role combines advanced hardware architecture with machine learning acceleration, focusing on TPU (Tensor Processing Unit) development. You'll work on architecture specifications, performance optimization, and cross-functional collaboration with various teams including SoC architecture, IP design, and software development.
The position requires deep expertise in computer architecture and silicon design, with a focus on machine learning accelerators. You'll be responsible for optimizing Performance, Power, and Area (PPA) based on machine learning workload analysis, and defining hardware IP architecture specifications that meet critical product goals. The role involves close collaboration with algorithm teams, power and performance teams, and hardware IP design teams.
As part of Google's mission to organize the world's information, you'll contribute to creating radically helpful experiences by combining Google's AI, Software, and Hardware capabilities. The team focuses on making computing faster, seamless, and more powerful, ultimately aiming to improve people's lives through technology. This is an opportunity to shape the future of Google's hardware experiences and drive innovation in silicon technology.
The ideal candidate will bring a strong background in TPU or parallel processor architecture, demonstrated experience in micro-architecture optimization, and expertise in machine learning workload analysis. You'll be working in New Taipei City, Taiwan, contributing to Google's next generation of hardware products that are used by millions worldwide.
Responsibilities For Senior Tensor Processing Unit Architect, Silicon
- Work on TPU architecture for next-generation Tensor SOC
- Define and deliver TPU hardware IP architecture specifications
- Perform detailed data analysis and tradeoff evaluations
- Propose architectural features/requirements for TPU integration
- Collaborate with implementation teams on design implementation
Requirements For Senior Tensor Processing Unit Architect, Silicon
- Bachelor's degree in Electrical Engineering, Computer Engineering, Computer Science, a related field, or equivalent practical experience
- 5 years of experience working with TPU or parallel processor architecture (such as VPU/DSP) and silicon design
- Master's degree or PhD preferred in relevant field
- Experience in micro-architecture, power and performance optimization
- Experience collaborating cross-functionally with SoC teams
- Experience in machine learning algorithm and workloads analysis
- Experience with architecting and designing TPU hardware IP
Jobs Related To Google Senior Tensor Processing Unit Architect, Silicon
