NVIDIA
Senior Production Engineer - DGX Cloud
$184K–$356K
US, CA, Santa Clara +1 · Senior · Full-time · Posted Oct 2, 2026
- Location
- US, CA, Santa Clara
US, Remote - Experience
- 8+ years.
- Education
- BS/MS in Computer Science or equivalent experience.
About the job
Build and operate software and automation that keep DGX Cloud control planes, model endpoints, and inference and agentic workloads reliable, scalable, and safe across cloud and on-premises environments.
What you'll do
- Develop production software, tooling, and automation for deployments, operations, routing, capacity management, and service recovery.
- Improve reliability through observability, SLIs and SLOs, safer rollouts, incident response, and durable fixes.
- Automate service enablement, model releases, deployment, upgrades, and ongoing operations across environments.
What they ask for
- 8+ years building or operating production services and large-scale distributed systems, including hands-on automation.
- Strong programming skills in Python, Go, or a comparable language, and experience developing production operations tools.
- Experience with infrastructure as code, configuration management, or GitOps; knowledge of Linux, Kubernetes, containers, cloud infrastructure, distributed systems, and networking.
- Understanding of SRE principles and experience using metrics, logs, and traces to improve reliability.
Nice to have
- Familiarity with vLLM, SGLang, PyTorch, TensorRT-LLM, NVIDIA Dynamo, CUDA, or NCCL, and GPU performance analysis.
- Experience with Kubernetes operators, fleet management, Terraform, Argo CD, CI/CD, safe deployments, or production AI inference and agentic workloads.
Pay
184,000 USD - 287,500 USD (base salary, Level 4); 224,000 USD - 356,500 USD (base salary, Level 5)
Tools
Python, Go, Linux, Kubernetes, AWS, Azure, Google Cloud, NVIDIA Dynamo
AI focus
Build and operate infrastructure for AI inference and agentic workloads, including model endpoints and production AI services.
Model-written summary · the original posting is authoritative