Compute System Architect

Overview

• The Compute System Architect team is dedicated to GPU compute and memory subsystems, providing opportunities to explore sophisticated cross-unit features in modern GPU architectures.
• The team works as the safety net of the chip.
• We catch function bugs in the HW by randomly generating tests and running them in various pre-silicon full chip platforms and debugging the failures.
• This work provides a good full-chip view of GPU and has a big space to innovate.
• What you’ll be doing: Explore innovative GPU composition and novel system functionalities related to processing and storage.
• Connect with GPU architecture designers to make advised and random functional testing plan which provides good coverage.
• Innovatively develop and improve infrastructure and methodology to generate tests.
• Massively generate, run and debug tests in various platforms, e.g., functional simulator, full chip and unit-level RTL, emulator and silicon.
• Build innovative tools to improve efficiency.
• What we need to see: Knowledge of computer architecture, compiler, assembly language.
• 4 + years working experience.
• Good understanding of GPU concept and pipeline, in terms of parallel computing and/or memory system.
• Familiar with Linux Good at C++ and Python development.
• MS or PhD or equivalent experience is a plus.
• Ways to stand out from the crowd: Knowledge and experience of CUDA programming and debugging.
• Random system development and work experience.
• Compiler experience NVIDIA is widely considered to be one of the technological world’s most desirable employers.
• We have some of the most forward-thinking and hardworking people in the world working for us.
• If you're creative, autonomous and love a challenge, we want to hear from you.