Senior Developer Relations Manager - Dynamo AI Inference

NVIDIA•Seattle, CA

About The Position

We are seeking a Senior Developer Relations Manager to build the developer ecosystem around NVIDIA Dynamo, our open-source framework for distributed AI inference. In this senior individual contributor role, you will help developers deploy and operate inference systems, build practical technical resources, and represent developer needs both in the community and inside NVIDIA!

Requirements

Degree in Computer Science, Engineering, or a related field, or equivalent experience.
8+ years of overall technology industry experience, including 4+ years in AI/ML infrastructure, model serving, or distributed systems.
Experience leading developer or partner programs across engineering, product, sales, marketing, and legal.
A background in AI inference with practical experience deploying and managing model-serving systems: configuring deployments, monitoring latency and throughput, scaling capacity, and troubleshooting reliability or performance issues.
Familiarity with inference engines such as vLLM, SGLang, or TensorRT-LLM, distributed serving stacks such as Dynamo or llm-d, and deploying and operating inference workloads on Kubernetes.
Experience working with open-source maintainers through issues, pull requests, and design discussions, and translating developer feedback into technical priorities.
A portfolio of technical guides, working demos, talks, or workshops you personally delivered that helped developers solve real problems.
Ability to explain inference architecture and performance tradeoffs to audiences from engineers to executives.

Nice To Haves

A record of earning developer trust externally and influencing decisions internally—for example, a community-reported problem you carried through to a shipped fix, API improvement, or simpler deployment workflow.
Experience working directly with the vLLM, SGLang, or Mooncake communities to co-create technical resources, recurring meetups, or hands-on workshops, with evidence of repeat participation, new contributors, and collaboration between projects.
Ability to identify patterns in developer feedback, serving-stack choices, and emerging inference workloads, and translate them into recommendations for product roadmaps, ecosystem investments, and partner priorities.

Responsibilities

Build the ecosystem with vLLM, SGLang, Mooncake, llm-d, and other inference projects through joint demos, integration guides, upstream contributions, and community programs that bring developers and maintainers together.
Develop runnable demos, sample code, technical documentation, and videos that explain Dynamo’s modular ecosystem and demonstrate its data center performance value.
Represent the developer community inside NVIDIA: turn feedback into concrete engineering and product requirements, influence priorities, and communicate progress back to developers.
Advocate externally through technical talks, live demos, workshops, and office hours.
Help developers troubleshoot real deployments and contribute to projects; track repeat participation, contributor growth, and issues resolved.