Senior SRE: AI Cloud Infra & GPU Platform

Devopsroles; Amsterdam; Hybrid; EUR 90,000 - 150,000; Full time

Benefits offered by this job

Competitive compensation

Career growth and learning

Flexibility and ownership

Collaborative and innovative culture

Impactful AI projects

International environment

Job summary

Nebius in Amsterdam is building a full‑stack AI cloud platform for data, models, and production deployment. This role focuses on reliability, performance, and observability of the inference stack, with a strong emphasis on Kubernetes, IaC, and GPU workloads.

You will design telemetry, tune autoscalers, and harden routing to ensure scalable, cost‑efficient operations. Collaboration with software engineers and ML teams is essential to success.

Qualifications

• Proven experience building reliable and scalable infrastructure for high‑throughput APIs.
• Strong knowledge of Kubernetes, observability, and incident response practices.
• Experience with IaC, Terraform, and GPU/ML deployment workflows.

Responsibilities

• Own the reliability, performance, and observability of the inference stack.
• Design telemetry pipelines (metrics, logs, traces) to derive actionable insights from terabytes of data.
• Tune Kubernetes autoscalers to improve GPU efficiency and reduce costs.
• Develop Terraform modules that bake resilience into new clusters and deployments.
• Harden request routing and retry logic to hide transient failures from users.
• Lead incident response and post‑mortem culture to prevent recurrence.

Skills

Infra design

SRE practices

Observability

Tools

Kubernetes

Prometheus

Grafana

Terraform

Python

Bash

GPU workloads

MLOps

Job description

Nebius in Amsterdam is building a full‑stack AI cloud platform for data, models, and production deployment. This role focuses on reliability, performance, and observability of the inference stack, with a strong emphasis on Kubernetes, IaC, and GPU workloads.

You will design telemetry, tune autoscalers, and harden routing to ensure scalable, cost‑efficient operations. Collaboration with software engineers and ML teams is essential to success.