Nvidia Senior Software Engineer - Data Center Rack Power Management Engineering 

United States, Texas 

9014428

What you’ll be doing:

• Drive next-generation power management solutions for scaling AI infrastructure using NVIDIA GPUs and CPU solutions.

• Collaborate with customers, product management, and architects to accurately define requirements and ensure high quality products on accelerating schedules.

• Develop architecture for power management at the server and rack levels, optimizing power consumption at the data center level.

• Produce detailed architecture specifications and validate through POCs. Educate partners on product architecture and incorporate their feedback.

• Coordinate the development of comprehensive architecture specs and design documents. Lead all aspects of product delivery by collaborating across teams.

• Conduct code reviews, improve unit testing, and ensure a robust test plan is in place.

• Support QA teams in leading product life cycles, ensuring their successful implementation. Effectively use Jira and other tools to articulate requirements and carry out plans.

• Contribute to all phases of product development, from definition and design to implementation, debugging, testing, and early customer support.

What we need to see:

• Looking for candidates with a BS, MS, or PhD in EE/CS or a related field (or equivalent experience) and a minimum of 8 years of experience in building rack or server management solutions.

• Experience evaluating power usage at the component level and reducing power consumption in server systems. Understanding of power metrics retrieval from devices.

• Expertise in firmware architecture and optimizing firmware for low latency APIs.

• Strong and proven skill in C/C++ and Python

• Proficient programming and debugging skills for server platforms.

• Experience with SCM tools (e.g., Git, Perforce) and project management tools like Jira.

• Excellent written and oral communication skills, strong work ethics, and a high sense of teamwork.

• A self-starter who finds creative solutions to complex problems and is hands-on with coding.

Ways to stand out from the crowd:

• Proven track record of improving perf/watt or TCO/watt for Data Centers.

• Experience developing OpenBMC solutions ideally with commits that have been upstreamed to the opensource repository.

• Active OCP and DMTF contributor in relevant areas with hands-on experience in x86 or ARM system architecture.