Senior SRE: AI Inference Platform (GPU, Kubernetes)

Slashhash; Netherlands; Hybrid; EUR 90,000 - 130,000; Full time

Job summary

Slashhash is seeking a Senior Site Reliability Engineer in the Netherlands to own the reliability and observability of a large-scale AI inference platform. You will design telemetry pipelines, build monitoring for massive production signals, and optimize Kubernetes and GPU resource usage.

The role requires deep Kubernetes, Terraform, Prometheus/Grafana, and Python/Bash expertise with a focus on reliability, observability, and GPU-heavy workloads.

Qualifications

• Senior level experience in site reliability or platform engineering with focus on AI workloads.
• Strong understanding of Kubernetes-based architectures and reliability practices.
• Proficient in observability pipelines and incident management processes.

Responsibilities

• Own the reliability, performance, and observability of the inference platform and its supporting infrastructure.
• Design, implement, and improve telemetry pipelines for metrics, logs, and traces.
• Build monitoring capable of processing large production signals and extracting insights.
• Configure and optimize Kubernetes for high availability and scalable GPU resources.
• Tune autoscaling to improve GPU resource efficiency.
• Develop Terraform modules embedding resilience into clusters and services.
• Improve request-routing, retry, and failure-handling to minimize outages.
• Develop automation to detect, isolate, and remediate incidents quickly.
• Create and maintain runbooks for incident response and procedures.
• Contribute to post-mortems and implement corrective actions to prevent recurrence.
• Define reliability practices for high-throughput APIs with alerting and SLOs.
• Investigate distributed-system failures across infra and app layers.
• Optimize systems from kernel to application layer and support GPU workloads.
• Collaborate with software engineers to embed reliability in product development.

Skills

Kubernetes

Prometheus

Grafana

Terraform

Python

Bash

Distributed Systems

SLOs

Infrastructure as Code

GPU Workloads

vLLM

Triton

Ray

MLOps

Incident Management

Tools

Terraform

Kubernetes

Prometheus

Job description

Slashhash is seeking a Senior Site Reliability Engineer in the Netherlands to own the reliability and observability of a large-scale AI inference platform. You will design telemetry pipelines, build monitoring for massive production signals, and optimize Kubernetes and GPU resource usage.

The role requires deep Kubernetes, Terraform, Prometheus/Grafana, and Python/Bash expertise with a focus on reliability, observability, and GPU-heavy workloads.