DevOps / Platform Engineer (Kubernetes / AI Infrastructure)

Stellenbeschreibung:

Purpose of the role

We’re looking for an experienced DevOps / Platform Engineer to help design, build, and operate the infrastructure behind our AI-powered platform. If you enjoy building reliable systems, automating everything, and enabling teams to ship quickly and safely — we’d love to talk.

Your mission

Build, maintain, and evolve our cloud infrastructure across modern platforms (primarily Azure)
Operate and scale Kubernetes clusters running production workloads
Manage containerized services using Docker, Kubernetes, and Helm
Design and maintain Infrastructure as Code with Terraform
Build and operate CI/CD pipelines using GitHub Actions; Plan and execute automated releases, deployments, and rollback strategies
Support customer environments, including onboarding, updates, and migrations into client Azure tenants
Implement strong infrastructure security, secrets management, and access control
Improve monitoring, logging, and alerting to ensure full system observability
Operate AI infrastructure components, including AI gateways (e.g., LiteLLM) and model-serving infrastructure
Work closely with Frontend, Backend, and AI teams to optimize deployments and platform reliability
Drive improvements in performance, reliability, cost efficiency, and automation
Maintain clear and useful technical documentation for infrastructure, deployments, and operational processes
Communicate infrastructure decisions clearly across engineering teams and stakeholders
Move fast and pragmatically for non-critical tasks, while being careful, structured, and reliability-focused for production systems

Your profile

Several years of experience as a DevOps, Platform, or Cloud Engineer running production systems
Strong experience operating Kubernetes environments
Deep understanding of Linux systems, networking, and OS-level performance and security
Strong Cloud Experience (Azure or another major cloud provider)
Experience with Terraform and Infrastructure as Code
Experience designing and operating CI/CD pipelines (GitHub Actions, Azure DevOps, etc.)
Experience with Docker, containerized workloads, and microservice platforms
Strong understanding of security best practices, secrets management, and compliance (e.g., GDPR)
Experience with Prometheus, Grafana, and centralized logging systems
Strong scripting skills (Bash / Python) and confidence working with YAML-heavy environments

Bonus

Experience migrating infrastructure between cloud providers
Exposure to AI/ML infrastructure, GPU workloads, or MLOps pipelines
Experience operating AI gateways such as LiteLLM or similar model routing layers
Experience supporting enterprise or multi-tenant SaaS environmentsExperience on OpenShift