Platform Engineer Kubernetes & AI Operations (m/w/d)

Job summary

The Platform Engineer builds and operates a Kubernetes platform for production enterprise applications, providing self-service capabilities and standardized deployment paths for development teams. The role also integrates and runs AI and LLM applications, including inference services and GPU resources, and improves operations through AIOps and observability across metrics, logs, and traces. Platform standards must address security and regulatory requirements, including DORA, MaRisk, and the EU AI Act.

Benefits

Qualifications

• Several years of hands-on Kubernetes experience in production environments.
• Knowledge of networking, storage, Kubernetes security, secrets management, and scripting with Python, Go, or Bash.
• Proficiency with Linux, Git, CI/CD, Helm, and infrastructure as code using Terraform or OpenTofu.
• Experience deploying and operating AI and LLM models, such as with vLLM, or using AI for automation.
• Ability to turn technical ideas into reliable platform solutions and work independently and methodically.
• Strong communication skills for explaining technical topics to teams and management.
• Very good German (at least C1) and good English.
• Experience in financial services or another regulated environment is an advantage.

Responsibilities

• Develop the Kubernetes platform for production enterprise applications as an internal product, with self-service capabilities and standardized deployment paths.
• Ensure secure, stable, and automated operation of the Kubernetes platform.
• Integrate AI and LLM applications into the existing infrastructure and operate inference services and GPU resources reliably.
• Use AI to modernize and automate IT operations, including monitoring, error analysis, and documentation.
• Establish end-to-end observability across metrics, logs, and traces, and continuously improve platform operations.
• Define operational, security, and automation standards for container and platform solutions, addressing requirements including DORA, MaRisk, and the EU AI Act.
• Document architecture and operations, lead knowledge-sharing workshops, and support colleagues in using the platform.

Skills

Languages

Work schedule

Industry

Relocation