Senior SRE — AI Inference Platform (GPU/Kubernetes)

Jobgether; Ireland; On-site; EUR 120,000 - 180,000; Full time

Benefits offered by this job

Competitive compensation

Learning opportunities

Ownership in your work

International team

Job summary

Token Factory in Ireland seeks a Senior Site Reliability Engineer to own the reliability, performance, and observability of a large-scale AI inference platform. You will optimize GPU-heavy workloads and ensure high-throughput APIs meet reliability and cost targets.

You'll design telemetry pipelines, build self-healing systems, and work closely with software and infrastructure teams to scale the platform. The role demands deep Kubernetes, Terraform, Prometheus, and Grafana expertise in a

Qualifications

• Significant experience in Site Reliability Engineering, Production Engineering, DevOps, or related infra discipline.
• Deep practical knowledge of Kubernetes in production environments.
• Strong experience with Prometheus and Grafana for monitoring and observability.
• Advanced experience with Terraform and IaC practices.
• Scripting skills with Python and/or Bash.
• Solid understanding of distributed systems and failure modes.
• Experience designing alerts, monitoring strategies, and SLOs for high-throughput services.

Responsibilities

• Own the reliability, performance, and observability of the inference platform and its infra.
• Design and improve telemetry pipelines for metrics, logs, and traces.
• Build monitoring solutions for large production signals.
• Configure Kubernetes for high availability and efficient GPUs.
• Tune autoscaling to optimize GPU resource utilization.
• Develop Terraform modules and IaC patterns for clusters and services.
• Improve request routing, retry, and failure handling mechanisms.
• Create automation and tooling to detect and remediate incidents.

Skills

Kubernetes

Prometheus & Grafana

Terraform

Python Bash scripting

GPU-heavy workloads

Incident management

Observability

SLOs & alerts

Tools

Kubernetes

Terraform

Prometheus

Grafana

vLLM/Triton/Ray

Job description

Token Factory in Ireland seeks a Senior Site Reliability Engineer to own the reliability, performance, and observability of a large-scale AI inference platform. You will optimize GPU-heavy workloads and ensure high-throughput APIs meet reliability and cost targets.

You'll design telemetry pipelines, build self-healing systems, and work closely with software and infrastructure teams to scale the platform. The role demands deep Kubernetes, Terraform, Prometheus, and Grafana expertise in a