System Software Engineer - Data Center Diagnostics

NVIDIA • Durham, NC

2d

About The Position

In this position, we are seeking system software engineers to work on next-generation rack-scale Data Center AI supercomputer systems. Our charter is to build applications to test and heavily stress GPUs, CPUs and networking devices, and to use those applications in silicon/system bring-up along with packaging such tools for customer use. The best candidates will have significant experience writing low level drivers to interface to HW, brought up a variety of low-speed and high-speed interfaces, have detailed knowledge of high speed buses such as PCIe, worked in both Linux user and kernel space, and have deep programming skills in C++ and Python Excellent interpersonal skills are required as this role will need an engineer to interface to architecture, HW design, manufacturing and field teams. In addition, the engineer will extensively use their knowledge of operating systems, computer architecture, memory and high-speed interfaces to provide robust and efficient solutions to validate and test next generation processors and systems. What you'll be doing: Working closely with architecture, hardware and driver teams through the product development lifecycle of computing and graphics processors, as well as compute products. Responsible for crafting software tools and infrastructure required for new chip development, validation, and productization. Assess new hardware features and architect manufacturing diagnostic tests using pre-beta GPU, CPU and network drivers This job will require a deep understanding of our hardware and software architectures

Requirements

• BS or MS degree in one of the areas of Electrical Engineering, Computer Engineering, Computers Science or equivalent experience
• 12+ years embedded software experience
• Experience writing low level software drivers and bringing up new HW
• Strong C/C++ and Python programming skills
• Familiarity with computer architecture, and ability to work close to hardware
• Background with PCIe, NVLink or server product technologies like InfiniBand and Ethernet
• Very strong problem solving and low level debugging skills
• Previous experience of working on a large system software code base is preferable
• Ability to self-manage, show leadership, and have good interpersonal skills

Responsibilities

• Working closely with architecture, hardware and driver teams through the product development lifecycle of computing and graphics processors, as well as compute products.
• Responsible for crafting software tools and infrastructure required for new chip development, validation, and productization.
• Assess new hardware features and architect manufacturing diagnostic tests using pre-beta GPU, CPU and network drivers

What This Job Offers

• Job Type: Full-time
• Career Level: Mid Level
• Number of Employees: 5,001-10,000 employees