Senior Production Engineer - DGX Cloud
Core
Build and operate production software, automation, and tooling for control plane services, model deployments, and inference/agentic workloads across NVIDIA DGX Cloud environments.
Role type
Senior Production Engineer (Infrastructure & SRE)
Builds
Reliable, scalable, and safe-to-operate AI inference and agentic services on distributed GPU/CPU infrastructure.
Domain
Cloud Infrastructure / AI Inference / Distributed Systems
Deliverable
production ML models
Required skills
Python, Go, Linux, Kubernetes, Cloud Infrastructure, Distributed Systems, Networking, SRE Principles, Infrastructure as Code, GitOps, Observability, Incident Response
Preferred skills
vLLM, SGLang, PyTorch, TensorRT-LLM, NVIDIA Dynamo, CUDA, NCCL, Kubernetes Operators, Terraform, Argo CD, CI/CD, AI Agents
Technologies
Kubernetes, AWS, Azure, Google Cloud, Terraform, Argo CD, vLLM, SGLang, PyTorch, TensorRT-LLM, NVIDIA Dynamo, CUDA, NCCL
Responsibilities
Build and operate production software and automation for control plane and inference services; Improve reliability of inference platforms through health validation, safer rollouts, and observability; Manage endpoint availability, inference routing, and capacity; Use IaC and GitOps for consistent deployments; Define and instrument SLIs/SLOs and use error budgets; Participate in on-call and incident response; Collaborate with model, platform, storage, and GPU teams.
Seniority
Senior, hands-on IC
