Senior Developer Relations Manager for Dynamo AI Inference

NVIDIA; Seattle (WA); In loco; USD 184.000 - 357.000; Tempo pieno

Descrizione del lavoro

NVIDIA seeks a Senior Developer Relations Manager in Seattle to shape the Dynamo ecosystem and help developers deploy inference systems. You will craft runnable demos, write docs, and drive open-source engagement while representing developer needs inside NVIDIA.

You will lead external talks, workshops, and office hours, and translate feedback into engineering and product priorities for scalable model-serving workloads.

Competenze

• Degree in CS, Engineering, or related field or equivalent experience.
• 8+ years in technology with 4+ years in AI/ML infra, model serving, or distributed systems.
• Experience leading developer or partner programs across engineering, product, sales, marketing, and legal.
• Background deploying and managing model-serving systems and inference workloads on Kubernetes.

Mansioni

• Build the developer ecosystem around NVIDIA Dynamo with demos, guides, and community programs.
• Develop runnable demos, sample code, documentation, and videos illustrating Dynamo's ecosystem and performance.
• Represent NVIDIA developer community, turning feedback into engineering and product priorities.
• Advocate externally via talks, live demos, workshops, and office hours; track participation and issues resolved.

Conoscenze

AI/ML infrastructure

Distributed systems

Open-source collaboration

Developer programs leadership

Formazione

Bachelor's degree in Computer Science, Engineering, or related field

Strumenti

vLLM

SGLang

Mooncake

llm-d

TensorRT-LLM

Kubernetes

Descrizione del lavoro

NVIDIA seeks a Senior Developer Relations Manager in Seattle to shape the Dynamo ecosystem and help developers deploy inference systems. You will craft runnable demos, write docs, and drive open-source engagement while representing developer needs inside NVIDIA.

You will lead external talks, workshops, and office hours, and translate feedback into engineering and product priorities for scalable model-serving workloads.