Senior Resiliency and Safety Architect, GPU Workloads and Failure Analysis

NVIDIA•Us, CA

15h

About The Position

We are now looking for a Resiliency and Safety Architect for GPU Workloads and Failure Analysis! 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 and Safety Architect to support the development of GPU (graphical processing unit) diagnostics for Resiliency in the Datacenter and Functional Safety in Autonomous Vehicles and Robots. 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 GPUs and SoCs powering product lines ranging from the rapidly growing field of artificial intelligence to self-driving cars and robots.

Requirements

Master’s or PhD degree in Computer Engineering, Electrical Engineering or closely related degree or equivalent experience.
At least 6+ years of relevant experience.
Familiarity with GPU and Networking Architectures, Computer Architecture basics (including caches, coherence, buses, direct memory access, etc.); Machine Learning/Deep Learning concepts.
Experience characterizing real world applications by identifying key behaviors and drilling down to low level implementation details including concurrency, occupancy, kernel launches, etc.
Scripting and automation with Python or similar.
Proficiency in C/C++.
Excellent interpersonal skills and ability to collaborate with on-site and remote teams.
Strong debugging and analytical skills.
Be self-driven and results oriented.

Nice To Haves

CUDA Programming
Understanding of GPU hardware architecture and AI workload execution on GPUs
Understanding factors causing silent data corruption in hardware
Familiarity with datacenter resiliency or functional safety.

Responsibilities

Characterize real world applications and customer test suites triggering hardware failures in NVIDIA GPUs and other system components that that evade existing hardware and software detection mechanisms.
Provide insights to NVIDIA diagnostics developers on the workload behaviors (e.g., execution patterns, memory access, communication, synchronization, concurrency) that stress hardware, to improve effectiveness of our diagnostic test suite, and optimize test time.
Workloads span datacenter AI and High-Performance Computing applications, as well as autonomous vehicle and industrial robotics safety.
Study silent data corruption, intermittent faults, and hard-to-reproduce failures in the field, including customer returns (RMAs), to establish root causes, and improve detection by diagnostics.
Design, develop, and validate CUDA software diagnostics kernels to run on Datacenter NVIDIA GPUs and Safety SOCs and identify potential hardware issues.
Collaborate with GPU and system architects, software teams to translate workload insights into new resiliency features
Develop and deploy automation and infrastructure for a resiliency and safety debug cluster.