Senior SRE - AI Inference Platform (GPU, K8s)

Jobgether; Lavamünd; Vor Ort; EUR 127.000 - 190.000; Vollzeit

Benefits dieser Stelle

Competitive compensation

Career growth

Learning opportunities

Ownership in work

International teams

Zusammenfassung

Token Factory is seeking a Senior Site Reliability Engineer to own reliability, performance, and observability for a large-scale AI inference platform. You will design telemetry pipelines, monitor production signals, and optimize GPU-heavy workloads with Kubernetes and IaC tooling.

You will collaborate with software and infra teams to build self-healing systems, automate incidents, and improve runbooks and post-mortems to prevent incidents.

Qualifikationen

• Significant experience in Site Reliability Engineering or Production Engineering.
• Deep practical knowledge of Kubernetes in production environments.
• Strong experience with Prometheus and Grafana for monitoring and observability.
• Advanced experience with Terraform and infrastructure-as-code practices.
• Strong scripting and automation skills using Python and Bash.
• Experience designing alerts, SLOs, and monitoring strategies for high-throughput services.
• Hands-on experience with GPU-heavy workloads or accelerator-based infra is valuable.

Aufgaben

• Own reliability, performance, and observability of the inference platform.
• Design telemetry pipelines covering metrics, logs, and traces.
• Build monitoring solutions for large production signal volumes.
• Configure Kubernetes for high availability, scalability, and resource efficiency.
• Tune autoscaling to optimize GPU resources.
• Develop and maintain Terraform modules and IaC patterns.
• Improve request-routing, retries, and failure handling.
• Develop automation to detect, isolate, and remediate incidents.
• Create runbooks for incident response and operations.
• Lead post-mortems and implement corrective actions.

Kenntnisse

SRE

Kubernetes

Prometheus

Grafana

Terraform

Python

Bash

Incident management

GPU workloads

MLOps

Tools

Kubernetes tooling

Terraform modules

Jobbeschreibung

Token Factory is seeking a Senior Site Reliability Engineer to own reliability, performance, and observability for a large-scale AI inference platform. You will design telemetry pipelines, monitor production signals, and optimize GPU-heavy workloads with Kubernetes and IaC tooling.

You will collaborate with software and infra teams to build self-healing systems, automate incidents, and improve runbooks and post-mortems to prevent incidents.