Principal Software Engineer Dynamo

2100 NVIDIA USA2100 NVIDIA USA·Remote(US, CA, Santa Clara)
Software Development
Excel

WFA Digital Insight

As demand for AI infrastructure specialists surged 25% in 2025, roles like this Principal Software Engineer position at NVIDIA are becoming increasingly crucial. With a focus on scalable AI systems and distributed inference, this role requires a unique blend of technical expertise and innovative thinking. Given NVIDIA's pioneering work in GPU technology, candidates should be prepared to tackle complex challenges and demonstrate a deep understanding of AI systems and software engineering.

Job Description

About the Role

NVIDIA is seeking a Principal Software Engineer to join the Dynamo project, an innovative platform for efficient and scalable inference of large language and reasoning models in distributed GPU environments.

Responsibilities

  • Build the Kubernetes deployment and workload management stack for Dynamo to facilitate inference deployments at scale
  • Develop robust, production-grade inference workload management systems that scale from a handful to thousands of GPUs
  • Architect and optimize the separation of prefill and decode phases across distinct GPU clusters to improve throughput and resource utilization
  • Contribute to embedding disaggregation for multi-modal models

Requirements

  • Expertise in software engineering, particularly in building scalable AI systems
  • Proficiency in languages such as Rust and Python
  • Experience with Kubernetes and GPU resource management

How to Stand Out

  • Familiarize yourself with NVIDIA's Dynamo project and its applications in distributed AI infrastructure to stand out in the interview process.
  • Showcase your proficiency in Rust and Python by sharing personal projects or contributions to open-source repositories.
  • Highlight your experience with Kubernetes and GPU resource management, and be prepared to discuss optimization techniques for distributed systems.
  • Prepare to discuss how you approach complex challenges in software engineering and distributed systems, and how you stay up-to-date with the latest developments in AI and GPU technology.

This is a remote position listed on WFA Digital, the platform for professionals who work from anywhere. Browse more remote jobs across all categories.