Senior Distributed Systems Engineer, AI Inference Factory

NVIDIA Corporation; New York (NY); Presencial; USD 184.000 - 288.000; Jornada completa

Descripción de la vacante

NVIDIA is seeking a senior engineer to design and build factory infrastructure and automation for NVIDIA Inference Microservices (NIMs). You will craft scalable, reliable automation to take AI models into deployable services across Cloud, on-prem, and Kubernetes, while improving observability and performance.

You will mentor teams, partner with model teams, and drive tech strategy with a focus on end-to-end deployment and validation for heterogeneous hardware/software environments.

Formación

• Advanced programming to build distributed and compute systems.
• Experience collaborating with cross-functional teams and architects.
• Mentorship and team growth across product groups.
• Deep expertise in distributed containerized applications using Docker, Kubernetes, Cloud Endpoints, Helm, and Prometheus.
• BS or MS in CS/CE or related field; 8+ years in performant microservice/cloud tooling roles.

Responsabilidades

• Develop a factory pipeline to take an AI model and produce a deployable, validated service across Cloud, On-prem and Kubernetes environments.
• Design interfaces, data models and schema, expanding observability of the factory pipeline and compute infra.
• Collaborate with AI model teams to optimize productivity and reliability across teams.

Conocimientos

Distributed systems

Microservices

Multi-team collaboration

Mentorship

Programming

Educación

BS or MS in Computer Science or related field

Herramientas

Docker

Kubernetes (K8s)

Prometheus

Cloud Endpoints

Helm

CI/CD pipelines

Descripción del empleo

NVIDIA is seeking a senior engineer to design and build factory infrastructure and automation for NVIDIA Inference Microservices (NIMs). You will craft scalable, reliable automation to take AI models into deployable services across Cloud, on-prem, and Kubernetes, while improving observability and performance.

You will mentor teams, partner with model teams, and drive tech strategy with a focus on end-to-end deployment and validation for heterogeneous hardware/software environments.