Senior Site Reliability Engineer — Token Factory (Inference Platform)
Salary not listed • Remote • Amsterdam, Netherlands; Berlin, Germany; London, United Kingdom; Prague, Czech Republic; Remote - Europe • Full-time
Posted 1y ago
This job has been open for more than 60 days. It may no longer be actively hiring, so check with the company before putting a lot into an application.
Job Location
Amsterdam, Netherlands; Berlin, Germany; London, United Kingdom; Prague, Czech Republic; Remote - Europe
Tech Stack
Remote Work Policy
Fully remote
Employment Type
Full-time
Categories
AI Infrastructure Engineer
About the job
Nebius is building a full-stack AI cloud platform for the global AI economy, supporting developers and enterprises from data and model training through to production deployment. Our Token Factory team is developing an inference platform for various foundation models, aiming to make them fast, reliable, and effortless to deploy at massive scale. We are seeking an engineer to ensure the flawless performance and graceful recovery of this platform under extreme load. This role involves owning the reliability, performance, and observability of the inference stack, from designing telemetry pipelines to tuning Kubernetes autoscalers and crafting resilient infrastructure. You will be instrumental in detecting, isolating, and remediating incidents quickly, and driving a post-mortem culture to prevent recurrence, all while meeting aggressive cost and reliability targets for scaling the platform.
Responsibilities
- Own the reliability, performance, and observability of the inference stack.
- Design and refine telemetry pipelines (metrics, logs, traces) for actionable insight.
- Tune Kubernetes autoscalers for GPU efficiency.
- Craft Terraform modules to embed resilience into new clusters.
- Harden request-routing and retry logic to ensure seamless user experience.
- Utilize automation and runbooks to detect, isolate, and remediate incidents rapidly.
- Drive post-mortem analysis to prevent future occurrences.
- Collaborate with software engineers to integrate reliability as a core feature.
Requirements
- Deep fluency with Kubernetes, Prometheus, Grafana, and Terraform.
- Proficiency in infrastructure-as-code practices.
- Comfortable scripting in Python or Bash.
- Understanding of alert design and SLOs for high-throughput APIs.
- Experience with distributed back-end systems in production.
- Experience with GPU-heavy workloads (e.g., vLLM, Triton, Ray).
- Background in MLOps or model-hosting platforms is beneficial.
- Ability to debug performance issues from kernel to application layer.
- Strong interest in building self-healing systems.
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