GPU Architect, Silicon

Google organizes the world's information and makes it universally accessible and useful, combining AI, Software, and Hardware to create helpful experiences.
Hardware
Mid-Level Software Engineer
In-Person
5+ years of experience
AI · Consumer

Description For GPU Architect, Silicon

Join Google's innovative hardware team as a GPU Architect, where you'll be at the forefront of developing custom silicon solutions that power Google's direct-to-consumer products. This role combines the best of Google's AI, Software, and Hardware expertise to create groundbreaking experiences used by millions worldwide.

As a GPU Architect, you'll be responsible for defining and architecting GPU cores for the Tensor SoC, working closely with Machine Learning, GPU Software, Android, and device teams. Your work will directly impact the performance and capabilities of Google's hardware products, particularly in graphics and machine learning applications.

The position requires strong technical expertise in computer architecture, GPU workload analysis, and hardware-software integration. You'll be working with cutting-edge technologies including Tensor SoC, utilizing your knowledge of GPU architecture, compiler optimization, and various graphics APIs (Vulkan, OpenGL, OpenCL).

This is an excellent opportunity for someone passionate about hardware architecture who wants to make a significant impact on Google's next-generation products. You'll be part of a diverse team that pushes boundaries and innovates in the hardware space, while enjoying Google's collaborative culture and comprehensive benefits.

The role offers the chance to work on challenging problems at scale, with access to Google's vast resources and the opportunity to influence the future of consumer hardware products. Your contributions will help shape the next generation of hardware experiences, delivering unparalleled performance, efficiency, and integration.

Last updated 18 hours ago

Responsibilities For GPU Architect, Silicon

  • Define Graphics Processing Unit (GPU) cores for the Tensor SoC based on GPU workload analysis
  • Propose architectural features/requirements for GPU to better integrate GPU with Tensor SoC to improve overall performance
  • Work with Google Machine Learning, GPU Software, Android and device teams to bring compelling experiences leveraging GPUs to Google
  • Enhance the overall Tensor SoC and software stack for GPU workloads

Requirements For GPU Architect, Silicon

Python
  • Bachelor's degree in Electrical Engineering, Computer Engineering, Computer Science, a related field, or equivalent practical experience
  • Experience in architecture performance analysis, tools, or simulators using C++ and Python or similar
  • Experience in using computer architecture concepts, such as pipelining, caches, virtual memory
  • Master's degree or PhD in Computer Science, Electrical Engineering preferred
  • Experience developing and analyzing workloads for GPUs preferred
  • Experience with developing optimizing compilers preferred
  • Knowledge of Vulkan, OpenGL, OpenCL, Android OS, Firmware preferred
  • Knowledge of ARM-based system architecture concepts preferred

Interested in this job?

Jobs Related To Google GPU Architect, Silicon

CMOS Device Engineer, Silicon

CMOS Device Engineer position at Google, focusing on silicon technology development and optimization for consumer products.

TPU Silicon Validation Engineer

TPU Silicon Validation Engineer position at Google, focusing on ASIC validation, test development, and system debugging for Tensor Processing Units.

Product Engineer, Global Manufacturing Engineering, Google Cloud

Product Engineer position at Google Cloud focusing on global manufacturing engineering and hardware development.

Power Engineer, Platforms, Engineering

Power Engineer position at Google, focusing on hardware and power systems design for data center infrastructure.

GPU Architect, Silicon

GPU Architect position at Google, focusing on developing custom silicon solutions and GPU cores for Tensor SoC, combining hardware architecture expertise with machine learning applications.