← All roles

Senior Site Reliability Engineer — Token Factory (Inference Platform)

Nebius· SRE
Apply on company site
Hybrid (Amsterdam / Europe)Full-timePosted 7mo ago

About the role

Senior SRE focusing on reliability, performance, and observability of Nebius's inference platform within Token Factory. Own telemetry, Kubernetes scaling, IaC, and incident response to scale the platform with high cost efficiency and reliability.

Responsibilities

  • Own the reliability, performance, and observability of the entire inference stack
  • Design and refine telemetry pipelines (metrics, logs, traces)
  • Tune Kubernetes autoscalers for GPU efficiency
  • Craft Terraform modules to bake resilience into new clusters
  • Harden request-routing and retry logic to prevent user-visible failures
  • Develop automation and runbooks to detect, isolate, and remediate problems during incidents
  • Drive post-mortem culture to prevent recurrence
  • Collaborate with software engineers to turn reliability into a feature for users
  • Aim to scale the platform smoothly while meeting cost and reliability targets

Qualifications

  • Deep fluency with Kubernetes, Prometheus, Grafana, Terraform, and infrastructure-as-code
  • Python or Bash scripting
  • Experience with alert design and SLOs for high-throughput APIs
  • Production experience with distributed back-ends
  • Experience shepherding GPU-heavy workloads (e.g., vLLM, Triton, Ray) or accelerator stacks
  • Background in MLOps or model-hosting platforms
  • Strong focus on self-healing systems, performance debugging from kernel to application layer
  • Collaborative experience with software engineers

Skills

Required:KubernetesPrometheusGrafanaTerraformPythonSLOs and alerting
Nice to have:Bash

Benefits

  • Competitive compensation
  • Career growth and learning opportunities
  • Flexibility and ownership
  • Collaborative and innovative culture
  • Opportunity to work on impactful AI projects
  • International environment and talented teams
Last updated Jul 8, 2026. Interested? Apply on the company site.
Nebius logo

About Nebius

The ultimate cloud for AI explorers

Discover the most efficient way to build, tune and run your AI models and applications on top-notch NVIDIA® GPUs.

AI CloudToken FactoryGPUKubernetesSlurmManaged servicesTerraformAPI
Company profileWebsite

More open roles at Nebius