All jobs
Senior Site Reliability Engineer — Token Factory (Inference Platform)
Nebius
Berlin +3 · HybridSenior (5–10 years)Full-timePosted 15 days ago
About the job
What you'll do
You will own the reliability, performance, and observability of the entire inference stack. Your role includes designing telemetry pipelines, tuning Kubernetes autoscalers, and creating automation for incident management.
What they're looking for
Success in this role requires deep fluency with various technologies including Kubernetes and Terraform, as well as experience with GPU-heavy workloads. A strong background in scripting and understanding of high-throughput APIs is essential.
Full description