Senior Site Reliability Engineer — Token Factory (Inference Platform)
Nebius London
Owns reliability, performance and observability of a large-scale inference platform serving text, vision and audio models. Day-to-day work spans telemetry pipelines, Kubernetes autoscaling, Terraform modules and request-routing resilience, with incident response and post-mortems. Requires deep Kubernetes, Prometheus, Grafana and IaC fluency plus GPU workload experience.