Senior DevOps / Platform Engineer – AI Infrastructure (m/w/d)

• Have operated production SaaS systems on self-administered Linux servers; experience only with fully managed cloud services is not enough.
• Use Docker and Docker Compose confidently in production, as well as reverse proxies or API gateways such as Traefik or Kong.
• Manage infrastructure with Terraform, NixOS or comparable tools and build CI/CD with GitHub Actions or similar systems.
• Have set up and tested PostgreSQL backups and restores yourself and are familiar with performance analysis and connection pooling.
• Have operated an observability stack yourself, for example with Grafana, Loki and Prometheus.
• Implement security in daily work, from permissions and secrets to security updates.
• Know the basics of RAG systems and their typical failure sources in operation, and can assess LLM serving trade-offs between latency, throughput, cost and operational effort.
• Drive topics independently, investigate unknown systems until understood, and prioritize by risk and impact.
• Use coding agents daily, including for infrastructure, and critically review their results before anything goes to production.
• Stay calm and clear during incidents, explain technical contexts understandably to non-technical people, and speak very confident German and English.

Engineering

The engineering team critically questions how it develops and continuously improves its processes, especially in agentic development.

Work in the office at least three days a week, with the remaining days wherever you like, and choose your own start time.

• Access to current frontier models and coding agents.
• Support for further training that fits your professional development.
• Access to a Wellpass membership.
• Virtual participation via the company's VSOP.
• Cook together almost every day.