Senior Site Reliability Engineer — AI Inference Platform

Nebius; United States; Remote; USD 150,000 - 210,000; Full time

Job summary

Nebius is building a full-stack AI cloud platform addressing data and model training to production deployment. We seek an engineer to own the reliability, performance, and observability of the entire inference stack in a high-demand environment.

Responsibilities include designing telemetry pipelines, tuning autoscalers, and crafting infrastructure-as-code modules. You will collaborate with software engineers to deliver self-healing, scalable systems that meet aggressive cost and reliability

Qualifications

• Deep fluency with Kubernetes, Prometheus, Grafana, Terraform, and infrastructure-as-code practices.
• You script in Python or Bash and understand alert design and SLOs for high-throughput APIs.
• Experience running GPU-heavy workloads with accelerator stacks (e.g., vLLM, Triton, Ray) in production.

Responsibilities

• Own reliability, performance, and observability of the inference stack.
• Design telemetry pipelines (metrics, logs, traces) turning terabytes of data into actionable insight.
• Tune Kubernetes autoscalers and craft Terraform modules to bake resilience into clusters; harden routing and retry logic.
• Lead post-mortems and drive the culture to prevent recurrence.

Skills

Kubernetes

Prometheus

Grafana

Terraform

Python

Bash

SRE practices

Observability

Tools

Kubernetes

Prometheus

Grafana

Terraform

Python

Bash

vLLM / Triton / Ray

Job description

Nebius is building a full-stack AI cloud platform addressing data and model training to production deployment. We seek an engineer to own the reliability, performance, and observability of the entire inference stack in a high-demand environment.

Responsibilities include designing telemetry pipelines, tuning autoscalers, and crafting infrastructure-as-code modules. You will collaborate with software engineers to deliver self-healing, scalable systems that meet aggressive cost and reliability