Senior SRE, AI Inference Platform — Scale GPU Cloud

FDE Times; Greater London; On-site; GBP 90,000 - 130,000; Full time

Benefits offered by this job

Competitive pay

Career growth

Flexibility

Collaborative culture

Impactful AI projects

International teams

Job summary

Nebius is building a full-stack AI cloud platform and seeks an engineer to own the reliability, performance, and observability of the inference stack.

You will design telemetry pipelines, tune Kubernetes autoscalers, bake resilience with Terraform, and drive post-mortems to prevent recurrence. You should be fluent with Kubernetes, Prometheus, Grafana, Terraform, and Python or Bash, with production experience and a passion for self-healing systems.

Qualifications

• Deep experience with Kubernetes, Prometheus, Grafana, Terraform and IaC.
• Proficient in Python or Bash with production-grade scripting.
• Experience with GPU-heavy workloads (vLLM, Triton, Ray) and MLOps.
• Strong focus on reliability, observability, and self-healing systems.

Responsibilities

• Own reliability, performance, and observability of the inference stack.
• Design telemetry pipelines (metrics, logs, traces) to distill insights.
• Tune Kubernetes autoscalers and Terraform modules for resilience and efficiency.
• Lead incident response, post-mortems, and preventive runbooks.

Skills

Kubernetes

Prometheus

Grafana

Terraform

Python

Bash

MLOps

GPU workloads

Tools

Terraform

Job description

Nebius is building a full-stack AI cloud platform and seeks an engineer to own the reliability, performance, and observability of the inference stack.

You will design telemetry pipelines, tune Kubernetes autoscalers, bake resilience with Terraform, and drive post-mortems to prevent recurrence. You should be fluent with Kubernetes, Prometheus, Grafana, Terraform, and Python or Bash, with production experience and a passion for self-healing systems.