AI Platform Engineer

This is a fully remote position, open to applicants in Germany.

📋 Description

• Design and manage a sovereign LLM platform, which includes an OpenAI-compatible gateway, model serving, and GPU infrastructure.

• Implement tailored knowledge integrations for customers (RAG) utilizing vector databases, embeddings, and reranking techniques.

• Oversee cost management, tenant isolation, data protection, and establish necessary guardrails.

• Create monitoring and observability systems for assessing the performance, quality, and utilization of AI services.

• Advance the container-based platform using Docker, Coolify, and Kubernetes technologies.

• Automate deployment processes and take charge of CI/CD workflows for internal development initiatives.

• Manage Linux, cloud, and database infrastructures while ensuring their stability, security, and availability.

• Develop and improve monitoring, logging, and alerting solutions.

• Actively contribute to shaping the architecture of both the platform and AI services.

• Establish Infrastructure as Code practices and standardized deployment methodologies.

• Ensure that operating models are compliant with data protection regulations and provide tenant security.

• Document solutions, share expertise within the team, and assess new technologies in the fields of platform engineering and AI.

⛳️ Requirements

• A degree in computer science, business informatics, or a similar qualification.

• Several years of experience in DevOps, platform engineering, or cloud/infrastructure environments.

• Strong practical experience in operating container-based applications and modern platforms.

• Experience in building and managing LLM and AI services in a production setting, preferably in self-hosted environments.

• Excellent knowledge of Kubernetes, Docker, and Linux.

• Familiarity with CI/CD pipelines, cloud platforms—particularly Azure—and PostgreSQL.

• Practical experience with LLM gateways, RAG architectures, vector databases, and model-serving solutions.

• Proficient Python skills for automation and integrations.

• Independent and structured work approach with a high level of ownership, along with a strong focus on security and data protection.

• A solid understanding of architecture and platform engineering principles.

🏝️ Benefits

• An open and collaborative company culture.

• A trust-based working environment.

• Comprehensive onboarding supported by the entire AIS team.

• Flat hierarchies, expedited decision-making processes, and a significant degree of freedom to shape your work.

• A strategic role with a substantial influence on the future landscape of the platform.

• The opportunity to work on sovereign LLM hosting and AI infrastructure.

• Modern infrastructure featuring Kubernetes, Docker, CI/CD, and cloud technologies.

• A chance to actively influence standards, processes, and architectural decisions.

• An individual professional development budget for conferences, certifications, and specialized training.

• Clearly defined career and development pathways.

• The opportunity to specialize as an AI Platform Engineer or LLMOps expert.

• A small, focused, and agile team with rapid decision-making processes.

• An open feedback culture that includes regular one-on-one meetings and retrospectives.