GPU Architect, Devices and Services
Employment Type: Full-Time
* Master's degree in Electrical Engineering or Computer Science, or equivalent practical experience
* Experience in object-oriented programming and algorithms
* Experience with GPU software and hardware pipeline
* Experience with computer architecture concepts
* PhD in Electrical Engineering or Computer Science
* 5 years of industry experience or equivalent
* Experience developing and analyzing workloads for GPUs
* Experience in GPU architecture performance analysis, tools, and simulators at different abstraction levels (Cycle Accurate, TLM, and/or Functional)
* Knowledge of ARM ASIC architecture
* Knowledge of OpenGL, OpenCL, Vulkan, Python, OS, Firmware, SW stack
About the job
As a GPU Architect, you will architect and configure the graphics processor, while collaborating with software and hardware architects to build compelling analysis of the GPU designs to justify decisions with relevant workloads. You'll also work on key workloads to assess the competitiveness of the design as part of the overall ASIC definition.
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.
* Define and configure third-party GPU cores for ASICs.
* Develop techniques and tools and perform hands-on PPA (Performance, Power, Area) tradeoff analysis.
* Work with Google ML, SW, and camera teams to leverage GPUs.
* Propose future architectural features/requirements for GPU and other vendors.