Principal Datacenter Resiliency Architect, RAS Features and Modeling

NVIDIA•Santa Clara, CA

21h

About The Position

We are now looking for a Principal Datacenter Resiliency Architect, RAS Features and Modeling! Today, NVIDIA is tapping into the unlimited potential of AI to define the next era of computing. An era in which our GPU acts as the brains of computers, robots, and self-driving cars that can understand the world. Doing what’s never been done before takes vision, innovation, and the world’s best talent. As an NVIDIAN, you’ll be immersed in a diverse, encouraging environment where everyone is inspired to do their best work. Come join the team and see how we can make a lasting impact on the world. We are now seeking a Resiliency Architect to support the development and validation of GPU (graphical processing unit) hardware and software resiliency features, including modeling reliability and availability from component to datacenter level. In this role, you will be a key member of a team of innovators, challenging the status quo and pushing beyond boundaries. You will have the opportunity to impact the industry's leading Datacenter GPUs and SOCs powering product lines for the growing field of artificial intelligence (AI) and high-performance computing (HPC).

Requirements

PhD degree in Computer Engineering, Electrical Engineering or closely related degree or equivalent experience.
At least 10+ years of relevant experience.
Strong Understanding of GPU and Networking Architectures, Computer Architecture basics (including caches, coherence, buses, direct memory access, etc.); Machine Learning/Deep Learning concepts.
Strong knowledge and industry expertise in either GPU hardware architecture or RAS features or both.
Proficiency in developing Reliability (FIT) models, AVF estimation.
Good understanding of Availability concepts, ECC/parity/CRC strategies.
Strong understanding of hardware/software interactions for error handling.
Scripting and automation with Python or similar.
Excellent interpersonal skills and ability to collaborate with on-site and remote teams.
Strong debugging and analytical skills.

Nice To Haves

Experience with network and high-speed interface resiliency.
Proven experience leading and delivering RAS features across hardware, software, and infrastructure teams
Strong understanding of resiliency and reliability trade-offs in AI data centers, including failure modes, mitigation strategies, and impact on large-scale training/inference workloads

Responsibilities

Architect hardware and software Resiliency features to improve system Reliability, Availability, Serviceability (RAS), and performance in the Datacenter.
Model and analyze RAS metrics like Failures in Time (FIT) for permanent and transient errors, and Availability from GPU to Rack to Datacenter.
Use models to identify gaps and drive RAS improvements.
Analyze field data on hardware interruptions and permanent failures; enhance RAS models to better correlate to field data; and ensure optimal fault attribution, containment, and recovery for hardware errors
Collaborate with architects, unit designers and software engineers to ensure alignment of design and verification requirements to architecture specifications.
Develop and implement comprehensive architecture verification testplans for resiliency features
Execute architecture testplans by developing test content, working with Software and Architecture teams to enable, run, and debug tests on Architecture models.
Support test debug on RTL, emulation, and silicon.
Run simulations to analyze Architectural Vulnerability Factor (AVF) and Liveness of on-die memory, flip-flops, and latches.