Remuneration
Not specified
Location
Deutschland
Visa sponsorship
Not specified
Job summary
Develops and operates a sovereign LLM platform, including an OpenAI-compatible gateway, model serving, and GPU infrastructure. The role builds RAG integrations and manages platform architecture, security, tenant isolation, cost controls, and observability, while maintaining containerized services and automating deployments with Kubernetes, Docker, Coolify, CI/CD, Linux, Azure, PostgreSQL, and Python.
Benefits
Individual training budget for conferences, certifications, and professional traCareer and development pathsComprehensive onboardingFlexible scope to shape platform standards, processes, and architectureOpen and cooperative working cultureRegular one-to-one meetings and retrospectives
Qualifications
- Degree in computer science, business informatics, or equivalent qualification
- Several years of experience in DevOps, platform engineering, cloud, or infrastructure
- Practical experience operating containerized applications and modern platforms
- Experience building and operating LLM and AI services, preferably in self-hosted environments
- Strong Kubernetes, Docker, and Linux skills
- Experience with CI/CD pipelines, cloud platforms—especially Azure—and PostgreSQL
- Practical experience with LLM gateways, RAG architectures, vector databases, and model-serving solutions
- Python skills for automation and integrations
- Strong architecture and platform understanding
Responsibilities
- Develop and operate a sovereign LLM platform, including its gateway, model serving, and GPU infrastructure
- Build customer-specific RAG integrations using vector databases, embeddings, and reranking
- Ensure cost control, tenant isolation, privacy, and guardrails
- Establish observability for AI service performance, quality, and usage
- Operate and improve containerized platforms using Docker, Coolify, and Kubernetes
- Automate deployments and manage CI/CD processes
- Maintain Linux, cloud, and database infrastructure for stability, security, and availability
- Develop monitoring, logging, and alerting solutions
- Shape platform and AI service architecture
- Establish Infrastructure as Code and standardized deployment processes
- Document solutions, share knowledge, and evaluate platform engineering and AI technologies
Skills
AzureDockerKubernetesLinuxPostgreSQLPythonOpenTelemetry
Degrees
Degree in computer science, business informatics, or equivalent qualification
Industry
IT servicesPlatform engineeringArtificial intelligence
Relocation
No