Senior Production Engineer - DGX Cloud
Core
Build and operate production software, automation, and tooling for NVIDIA DGX Cloud's control plane services, model deployments, and inference/agentic workloads across multi-cloud and on-prem environments.
Role type
Senior Production Engineer (SRE)
Builds
Reliable, scalable AI inference and agentic services on DGX Cloud
Domain
Cloud Infrastructure / AI Inference / Distributed Systems
Deliverable
production ML models
Required skills
Python, Go, Linux, Kubernetes, Cloud Infrastructure, Distributed Systems, Networking, SRE Principles, Observability (Metrics/Logs/Traces), Infrastructure as Code, GitOps
Preferred skills
vLLM, SGLang, PyTorch, TensorRT-LLM, NVIDIA Dynamo, CUDA, NCCL, Kubernetes Operators, Terraform, Argo CD, AI Agents
Responsibilities
Build automation for control plane and model deployments; Improve reliability of inference platforms via health validation and rollouts; Manage endpoint availability and capacity; Define and instrument SLIs/SLOs; Participate in on-call and incident response; Collaborate with model and infrastructure teams
Seniority
Senior, hands-on IC
