Senior SRE — AI Inference Platform & GPU Cloud

United States Digital Space LLC; Amsterdam; Hybrid; EUR 120,000 - 160,000; Full time

Benefits offered by this job

Competitive compensation

Career growth and learning

Flexibility and ownership

Collaborative culture

Impactful AI projects

International environment

Job summary

Cloud is seeking an engineer to own the reliability, performance, and observability of its inference stack. You will design telemetry pipelines and tune Kubernetes autoscalers for efficient GPU utilization.

Ideal candidates will have deep production experience with GPU-heavy workloads (vLLM, Triton, Ray) and a strong background in MLOps. Collaboration with software teams is essential to make reliability a feature.

Qualifications

• Fluency in infrastructure as code (Kubernetes, Terraform) and observability tooling.
• Experience managing GPU-heavy workloads (vLLM, Triton, Ray) in production.
• Background in MLOps or model-hosting platforms is highly valued.

Responsibilities

• Own reliability, performance, and observability of the inference stack.
• Design telemetry pipelines: metrics, logs and traces for high-volume APIs.
• Tune Kubernetes autoscalers to improve GPU efficiency and cost.
• Build Terraform modules to bake resilience into new clusters.
• Harden request-routing and retry logic and drive post-mortem culture.
• Collaborate with software engineers to treat reliability as a feature.

Skills

Infrastructure fluency

GPU workload experience

MLOps background

Tools

Kubernetes

Prometheus

Grafana

Terraform

Python

Bash

vLLM

Triton

Ray

Job description

Cloud is seeking an engineer to own the reliability, performance, and observability of its inference stack. You will design telemetry pipelines and tune Kubernetes autoscalers for efficient GPU utilization.

Ideal candidates will have deep production experience with GPU-heavy workloads (vLLM, Triton, Ray) and a strong background in MLOps. Collaboration with software teams is essential to make reliability a feature.