Senior RAS Architect - Datacenter CPU and SOC

For two decades, we have pioneered visual computing, the art and science of computer graphics - with our invention of the GPUs, the engine of modern AI technologies, the field has expanded to encompass AI-powered video games, social networking and web search, IC & other product design, medical diagnosis, and scientific research. Today, visual computing is the critical computing engine for deep learning-based AI including ChatGPT, becoming increasingly central to how people entertain and interact, and there has never been a more exciting time to join us to enable visual computing and AI to the next chapter. We are looking for one Architect to drive key aspects of RAS/Resilience features for our next-generation products for AI Applications. We are expecting you to bring deep knowledge and experience in RAS/Resilience testing, characterization, analysis, benchmarking, and risk assessment of CPU, DRAM, and AI cluster systems.

What you’ll be doing:

• Drive Memory RAS requirements for data-center CPU.

• Own the system RAS/Resilience models, Benchmarking and Risk assessment.

• Lead the data analysis of RAS/Resilience logs to refine, revise and overhaul test methodology and manufacturing flows; influence and drive software tools/infrastructure required for new product development, validation, and productization.

• Opportunity to work closely and partner with architecture, hardware, software, and product engineering teams through the product development lifecycle.

• Be ready to be challenged to assess new hardware features and architect manufacturing RAS tests, flows, methodologies.

• You'll nurture a deep understanding of NVIDIA's AI hardware and software architecture.

What we need to see:

• BS or higher in EE, CE, CS, Mathematics, or equivalent experience.

• 12+ years proven hands-on experiences in design, testing, benchmarking, and risk assessment of system RAS / Resiliency features of large Compute or AI or HPC systems.

• Proficient in Compute System RAS/Resilience model theory and methodology.

• Proficient in HPC or AI system architecture and Cluster Interconnect technologies.

• Proficient in using test equipment, Linux commands and benchmark utilities to test and trouble-shoot compute system RAS & Resiliency features.

• Strong problem-solving and trouble-shooting expertise; and institutionalizing root-cause analysis.

• Self-initiative, strong interpersonal skills, and flexibility to adapt to new technologies.

• Solid Knowledge and/or Experience in HPC or MLPerf benchmarking is a plus.

NVIDIA is widely considered to be one of the technology 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 and autonomous, we want to hear from you!