Senior SRE Engineer

at Nvidia
USD 148,000-276,000 per year
SENIOR
✅ On-site

Used Tools & Technologies

Not specified

Required Skills & Competences

Ansible @ 4 Go @ 7 Grafana @ 4 Kubernetes @ 4 Linux @ 4 Prometheus @ 4 IaC @ 4 Terraform @ 4 Python @ 7 GitHub @ 4 GitHub Actions @ 4 Bash @ 7 Helm @ 4 SRE @ 4 Microservices @ 7 Android @ 4 API @ 4 OpenTelemetry @ 4 GPU @ 4 Deep Learning @ 4 Observability @ 4 AI @ 4 Robotics @ 4

Details

NVIDIA is seeking a passionate, motivated, and technical Engineer to join its Infrastructure, Planning, and Processes organization as a Senior SRE Engineer. You will own and scale the company's internal CI as a Service platform, including shared GitLab CI and GitHub Actions infrastructure used by thousands of engineers. The role manages multi-OS and multi-hardware build and test environments (Windows, Linux, Android, NVIDIA GPUs, Tegra processors) and collaborates with software teams across graphics, mobile, deep learning, robotics, and autonomy.

Responsibilities

  • Develop, operate, and scale a multi-tenant CI platform built on GitLab CI and GitHub Actions: runner fleets, shared caches, artifact storage, and secrets brokering.
  • Own the Kubernetes substrate end-to-end: cluster lifecycle, upgrades, autoscaling, node pools for GPU/CPU/ARM workloads, network and storage policy, and operators/controllers that schedule runner pods on demand.
  • Drive reliability and capacity engineering: define and manage SLOs/SLIs and error budgets for queue time, job success, and runner availability; participate in on-call, incident response, postmortems, and implement structural fixes to reduce toil.
  • Build self-service layers: pipeline templates, reusable workflows, golden images, policy-as-code, and guardrails to enable fast, secure onboarding for product teams.
  • Continuously improve developer experience: reduce cold-start times, optimize caching, enable hermetic builds, test sharding and flakiness reduction, and provide deep observability into pipeline performance and cost per team.

Requirements

  • 5+ years in SRE/platform roles with strong fundamentals in SLO/SLI creation, incident command, resource planning, performance tuning, and production Linux administration at scale.
  • Deep Kubernetes administration experience: CRDs and operators, HPA/VPA/cluster-autoscaling, ingress, service mesh, RBAC, network policies, storage classes, and advanced troubleshooting skills.
  • Hands-on expertise with GitLab CI and GitHub Actions at scale: runner architecture, executor tuning, self-hosted runner controllers (ARC, GitLab-runner Helm chart), cache and artifact strategy, and pipeline development (DAGs or equivalent).
  • Strong scripting and automation in Python, Go, and bash. Production experience with IaC/configuration management tooling such as Terraform, Helm, and Ansible.
  • Experience with GitOps tools (Argo CD, Flux).
  • BS/MS in Computer Science or equivalent experience. Experience building observability systems (Prometheus, Grafana, Loki/ELK, OpenTelemetry) and shipping platforms used by many engineers.

Ways to stand out

  • Strong understanding of containerization and microservices architecture. Kubernetes certifications (CKA, CKS, CKAD) preferred.
  • Experience building or extending CI control planes: custom runner schedulers, autoscaling, webhook routers, or orchestration on top of GitLab/GitHub APIs.
  • Prior experience with large-scale operations teams, data center operations, and algorithmic approaches to scaling problems.

Compensation and benefits

  • Base salary ranges provided by location/level: Level 3: 148,000 USD - 235,750 USD; Level 4: 176,000 USD - 276,000 USD.
  • Eligible for equity and company benefits (link provided in original posting).

Additional information

  • Applications accepted until July 6, 2026.
  • NVIDIA uses AI tools in its recruiting processes and is an equal opportunity employer committed to inclusion.