What will you do?

Build and operate Kubernetes environments that host AI engineering tools, internal model gateways, retrieval components, workflow services, CI/CD runners, and documentation services

Implement GitOps and Infrastructure as Code patterns for reproducible provisioning, configuration, policy enforcement, platform upgrades, and disaster recovery readiness

Manage private registries, package mirrors, secrets, identity integration, network segmentation, storage classes, backup routines, and controlled connectivity models

Provide observability for engineering workloads, including metrics, logs, traces, GPU and CPU utilization, service health, cost signals, and operational runbooks

Work with software, security, and architecture teams to ensure the platform supports AI-assisted SDLC workflows without creating uncontrolled data exposure or audit gaps
Examples of market tools, models, and platform components expected

Platform tooling such as Kubernetes, Helm, Terraform, Ansible, ArgoCD, Crossplane, GitLab runners, Jenkins agents, private registries, and internal package mirrors.

AI platform components such as vLLM, Ollama, OpenAI-compatible gateways, Qdrant or similar vector stores, Open WebUI, Continue-compatible endpoints, and workflow services.

Observability and operations stacks such as Prometheus, Grafana, Loki, OpenTelemetry, ELK/OpenSearch, Alertmanager, SRE runbooks, and incident management tooling.

Security and governance components such as Vault, Keycloak, network policies, RBAC, admission controls, image scanning, SBOM tooling, and audit logging.

Infrastructure awareness covering GPU-backed nodes, CPU-only fallback, storage performance, network isolation, proxy patterns, on-premise environments, and dedicated landing zones.

You will succeed if you:

Have 5+ years in SRE, platform engineering, DevOps, cloud infrastructure, or operations roles with strong Kubernetes and Linux expertise.

Proven experience building and operating production-grade engineering platforms with GitOps, Infrastructure as Code, observability, and operational runbooks.

Hands-on skills in Terraform, Ansible, Helm, Python or shell scripting, CI/CD runners, private registries, and secure configuration management.

Good understanding of networking, storage, secrets, access control, monitoring, backup, disaster recovery, and operational hardening in high-security environments.

Comfortable supporting AI-enabled engineering workloads in sovereignty-driven contexts where isolation, controlled data handling, reliability, and auditability are mandatory.

 

Why should you choose us?

We believe in balance between work and personal life. An attractive and extensive work-life balance portfolio guarantees lasting motivation for employees and thus a better quality of life, promotes physical and mental well-being and contributes to a positive work environment. All this with the aim of providing more freedom in reconciling work, career growth, private life and individual lifestyle. Therefore we offer to our employees over 25 different benefits to improve their personal and professional life in these areas:

• Financial benefits
• Benefits with focus on learning and development *
• Benefits with focus on health and sport *
• Benefits with focus on family and work - life balance
• Other benefits *

For more information about our benefits click to Benefits.

Benefits with * are applicable also to part-time positions.
This information may be subject to changes and other internal rules.

Wage (gross)

From 2 100 EUR/monthFinal salary is negotiable.
We are offering base salary depending on seniority level and previous experience of candidate. In addition to base salary we provide variable part and other financial benefits.

Contact