Principal Platform Software Engineer - RAS

Details

NVIDIA is developing next-generation rack-level solutions for scaling AI supercomputing platforms based on the GH200 superchip. The role focuses on fleet management, platform health monitoring, fault remediation, and product delivery for GPU and Grace-based AI infrastructure.

Responsibilities

• Drive next-generation fleet management solutions for scaling AI infrastructure using NVIDIA GPUs and Grace solutions.
• Work with customers, product management, and architects to define implementation requirements and accelerate product development.
• Architect fleet health monitoring and fault-remediation solutions at scale, using both in-band and out-of-band capabilities.
• Develop detailed architecture specifications and perform proofs of concept to validate designs.
• Educate customers about product architecture and incorporate feedback into product improvements.
• Write architecture specifications and design documents, and own end-to-end product delivery across teams.
• Conduct code reviews for implementations based on architecture specifications.
• Work with development teams to improve unit testing and establish appropriate test plans.
• Drive product life cycles with QA teams to productize code and act as a product owner.
• Define requirements using Jira and bug-management tools, and develop end-to-end execution plans with other managers.
• Contribute to all phases of product development, including product definition, architecture, design, implementation, debugging, testing, and early customer support.

Requirements

• Bachelor's, master's, or doctoral degree in electrical engineering, computer science, or a related field, or equivalent experience.
• 15 or more years of hands-on coding experience.
• Strong knowledge of time-series databases such as InfluxDB and Prometheus.
• Strong knowledge of building and consuming REST APIs; Redfish experience is a plus.
• Strong knowledge of telemetry visualization solutions such as Grafana and InfluxDB.
• Strong knowledge of firmware architecture and optimizing firmware for low-latency APIs.
• Strong knowledge of analyzing algorithms for time and space complexity and projecting system resource requirements.
• Proven record of developing scalable solutions.
• Strong, demonstrable programming skills in C/C++ and Python.
• Programming and debugging experience with server platforms.
• Experience with source-control management tools such as Git or Perforce and project-management tools such as Jira.
• Excellent written and oral communication skills, work ethic, teamwork, commitment to quality, and ability to complete tasks consistently.
• Self-directed approach and ability to develop creative solutions to complex problems while remaining hands-on with coding.

Preferred Qualifications

• Experience building telemetry collection and analysis engines.
• Experience with Redfish and notification systems such as PagerDuty.
• Active contributor to Open Compute Project or DMTF initiatives in relevant areas.
• Hands-on experience with x86 or ARM system architecture.
• Familiarity with confidential computing.
• Experience with machine learning and multivariable optimization techniques.

Benefits

• Equity and employee benefits.
• NVIDIA is an equal opportunity employer committed to an inclusive work environment.

Applications will be accepted at least until August 3, 2026. This posting is for an existing vacancy.