Senior SRE - Inference Platform for GPU Cloud

Nebius Group; United States; Remote; USD 140,000 - 190,000; 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 and talented

Job summary

Nebius is seeking an engineer to own the reliability, performance, and observability of its full inference stack. You will design telemetry, tune Kubernetes autoscalers, and harden routing and retry logic to ensure fault-tolerant operations at scale.

Proficiency in Kubernetes, Prometheus, Grafana, Terraform, and Python or Bash is essential. The role emphasizes building self-healing systems and collaborating with software engineers to deliver dependable AI infrastructure.

Qualifications

• Deep familiarity with Kubernetes, Prometheus, Grafana and Terraform.
• Strong scripting in Python or Bash and production-grade telemetry design.
• Experience with GPU-heavy workloads and MLOps is a plus.
• Proven track record in building reliable, scalable infrastructure.

Responsibilities

• Own reliability, performance, and observability of the inference stack.
• Design telemetry pipelines (metrics/logs/traces) for large-scale signals.
• Tune autoscalers and infrastructure as code to optimize GPUs and clusters.
• Lead incident response, post-mortems, and prevention of recurrence.

Skills

Kubernetes

Prometheus

Grafana

Terraform

Python

Bash

MLOps

GPU workloads

Tools

Terraform

Docker

Kubernetes

Job description

Nebius is seeking an engineer to own the reliability, performance, and observability of its full inference stack. You will design telemetry, tune Kubernetes autoscalers, and harden routing and retry logic to ensure fault-tolerant operations at scale.

Proficiency in Kubernetes, Prometheus, Grafana, Terraform, and Python or Bash is essential. The role emphasizes building self-healing systems and collaborating with software engineers to deliver dependable AI infrastructure.