What you move

You are responsible for the operation and further development of the hybrid AI platform (OpenShift & Azure) and ensure stability, scalability, high availability and efficient GPU utilization.

You ensure the smooth operation of the AI ​​operations stack (e.g., MLflow, Dagster, vLLM, Triton).

You are responsible for the deployment and serving of LLM and ML models both on the on-prem platform (OpenShift) and via Azure services (e.g. Azure AI Foundry).

Operation and optimization of CI/CD pipelines and Infrastructure as Code. You define deployment and configuration standards and ensure security, compliance, and vulnerability management.

You ensure a robust data foundation (RDBMS, Object Storage, NoSQL, Backup & Recovery) and support migrations to and between On-Prem and Azure.

You will further develop the AI ​​platform into existing observability stacks and ensure stable platform operation (OpenTelemetry, Splunk, Dynatrace, Azure Monitor).