Senior SRE - AI Inference Platform, Scale & Reliability

Nebius; Greater London; On-site; GBP 100,000 - 140,000; Full time

Benefits offered by this job

Competitive compensation

Career growth and learning opportunity

Flexibility and ownership

Collaborative and innovative culture

Opportunity to work on impactful AI

International environment and talented

Job summary

Nebius in London is building a cutting‑edge AI cloud platform. This role owns the reliability, performance and observability of the entire inference stack, with hands‑on work on GPUs, Kubernetes and scalable cloud infrastructure.

You will implement telemetry pipelines (metrics, logs, traces), tune autoscalers with Kubernetes, craft Terraform modules, and harden routing and retries. You’ll drive post‑mortems to prevent recurrence while pushing for cost‑effective, high‑reliability operations that

Qualifications

• Proven experience with Kubernetes-based infrastructure.
• Deep knowledge of Prometheus, Grafana, and Terraform.
• Experience with GPU workloads and ML deployment pipelines.
• Background in MLOps or model-hosting platforms.

Responsibilities

• Own reliability, performance and observability of the inference stack.
• Design telemetry pipelines for metrics, logs and traces.
• Tune autoscalers and Terraform modules to improve efficiency.
• Lead post-mortems and drive remediation to prevent recurrence.

Skills

Python

Bash scripting

SRE fundamentals

Tools

Kubernetes

Prometheus

Grafana

Terraform

Job description

Nebius in London is building a cutting‑edge AI cloud platform. This role owns the reliability, performance and observability of the entire inference stack, with hands‑on work on GPUs, Kubernetes and scalable cloud infrastructure.

You will implement telemetry pipelines (metrics, logs, traces), tune autoscalers with Kubernetes, craft Terraform modules, and harden routing and retries. You’ll drive post‑mortems to prevent recurrence while pushing for cost‑effective, high‑reliability operations that