AI & Analytics DevOps Engineer

Quick Facts

• Focus: DevOps for secure, on-premise Generative AI and agentic LLM/analytics products
• Environment: Kubernetes/OpenShift with CI/CD and monitoring
• Compliance: IT-Grundschutz and German national security requirements

Description

You will deploy, operate, and maintain AI and Analytics products with an emphasis on generative AI and agentic LLMs in secure, on-premise national environments. The role partners with the AI & Data Analytics Product Owner to deliver AI releases through robust CI/CD practices and to ensure infrastructure compliance with IT-Grundschutz and other German security requirements. You will also design automation, monitoring, documentation, and resilience measures for air-gapped operations.

Responsibilities

• Oversee deployment, operation, and maintenance of AI & Analytics products and services in secure on-premise environments
• Facilitate continuous integration and delivery of AI releases; validate solutions and adherence to DevOps practices
• Manage compliance with IT-Grundschutz and German national security requirements in coordination with the Security Office
• Design, deploy, and administer AI/analytics applications via CI/CD pipelines for restricted networks
• Ensure continuous availability, performance, and monitoring of local generative AI apps on OpenShift and Kubernetes
• Build automated workflows/tools to streamline delivery for development and product teams
• Create technical documentation, architecture diagrams, runbooks, and SOPs to support audit readiness
• Participate in incident response and contribute to disaster recovery strategies for air-gapped setups
• Conduct technical evaluations and proof-of-concept testing for emerging orchestration and GPU runtimes
• Monitor and optimize GPU and other on-premise resource usage

Requirements

• Master’s degree in Computer Science, Cybersecurity (Distributed Systems/MLOps/DevSecOps), IT, Engineering, or related field
• At least 3 years of DevOps and continuous delivery experience
• Strong container orchestration experience (Kubernetes/OpenShift) and Docker/Podman
• Hands-on CI/CD experience (Jenkins or GitLab CI) and monitoring (Prometheus or Grafana)
• Familiarity with AI/ML lifecycle and local AI model serving (GPU resource management, vLLM) plus scripting in Python/Bash/Go
• Practical understanding of BSI IT-Grundschutz, DevSecOps, and security controls for air-gapped environments
• Strong collaboration, problem-solving, and communication skills for multidisciplinary teams and auditors
• Security clearance requirement: must hold or be eligible for clearance by recognized authorities
• Fluent German and English with excellent writing skills

Benefits

• Permanent role with options for reduced weekly hours and an adapted scope of tasks
• 30 days of annual leave
• Flexible and mobile working options
• Professional development and international career opportunities
• Health programs
• Diverse and inclusive working environment