Principal SDN Engineer - Cloud Networking & Observability

NVIDIA Corporation; United Kingdom; Remote; GBP 180,000 - 230,000; Full time

Job summary

NVIDIA Corporation is seeking a Principal System Software Engineer, Software Defined Networking, to design, build, and operate scalable SDN solutions for AI clouds hosting GPU-accelerated workloads.

You will own the full SDN stack lifecycle—from control and data plane software design to production reliability, observability, and incident response, collaborating with SRE, DevOps, and network teams to ensure SLAs are met in large-scale cloud environments.

Qualifications

• BS/MS in Computer Science or equivalent blend of education and experience.
• 15+ years of software development in large-scale distributed environments.
• Expert-level knowledge of OVN, OVS, OpenFlow and modern network protocols.
• Strong programming in C and Go; Bash and Python scripting.

Responsibilities

• Design and develop multi-tenant cloud SDN control and data plane software (OVS/OVN/OpenFlow).
• Build Infrastructure-as-a-Service virtual network orchestration using gRPC and REST for tenant workloads.
• Drive upstream contributions to OVN-Kubernetes and related open-source projects.
• Develop software for network observability — monitoring, telemetry, and performance analysis.
• Operate and support OVS-OVN based SDN solutions in NVIDIA AI Cloud environments.
• Own end-to-end observability for the SDN stack — monitoring, alerts, tracing, dashboards.
• Design and maintain CI/CD pipelines (GitLab) across Linux host networking, OVS, OVN, and Kubernetes CNIs.
• Implement GitOps approaches for secure, seamless integration with cloud infrastructure.
• Collaborate with SRE, DevOps, and network engineering teams on production readiness.

Job description

NVIDIA Corporation is seeking a Principal System Software Engineer, Software Defined Networking, to design, build, and operate scalable SDN solutions for AI clouds hosting GPU-accelerated workloads.

You will own the full SDN stack lifecycle—from control and data plane software design to production reliability, observability, and incident response, collaborating with SRE, DevOps, and network teams to ensure SLAs are met in large-scale cloud environments.