AI Platform Engineer (all genders)

Job summary

Develop and operate a sovereign LLM platform, implement customer-specific knowledge connections, and ensure cost control and data protection. Establish monitoring for performance and quality, automate deployments, and manage Linux, cloud, and database infrastructure.

Qualifications

• Degree in Computer Science or a comparable qualification.
• Several years of experience in DevOps, platform engineering, or cloud/infrastructure environments.
• Practical experience in operating container-based applications and modern platforms.
• Experience in building and operating LLM and AI services, ideally in self-hosted environments.
• Strong knowledge of Kubernetes, Docker, and Linux.
• Experience with CI/CD pipelines, cloud platforms (especially Azure), and PostgreSQL.
• Practical experience with LLM gateways, RAG architectures, vector databases, and model serving solutions.
• Solid Python skills for automation and integrations.
• Independent and structured working style with high personal responsibility and awareness of security and data protection.
• Strong understanding of architecture and platforms.

Responsibilities

• Develop and operate a sovereign LLM platform including OpenAI-compatible gateway, model serving, and GPU infrastructure.
• Implement customer-specific knowledge connections with vector databases, embeddings, and reranking.
• Ensure cost control, tenant separation, data protection, and guardrails.
• Establish monitoring and observability for performance, quality, and usage of AI services.
• Develop and operate a container-based platform using Docker and Kubernetes.
• Automate deployments and manage CI/CD processes for in-house developments.
• Manage Linux, cloud, and database infrastructure ensuring stability, security, and availability.
• Build and enhance monitoring, logging, and alerting solutions.
• Actively shape the architecture of platform and AI services.
• Establish Infrastructure as Code and standardized deployment processes.
• Ensure data protection compliant and tenant-safe operating models.
• Document solutions, share knowledge within the team, and evaluate new technologies in platform engineering and AI.

Skills

Relocation