Project: deployment of a local AI server (LLM) based on Ollama/OpenWebUI, and development of a RAG assistant that answers user questions based on a knowledge base.
Initial setup, configuration and hardening of a Linux server (GPU) for local LLM deployment
Firewall configuration, TLS 1.3, patch/vulnerability management
Running services without root privileges (dedicated service account), minimal container privileges
Reverse proxy/WAF configuration in front of the API and web interface
Logging and monitoring setup (including syslog)
Role-based access configuration and separation of users/environments (multi-tenancy)
Solid hands-on experience administering and hardening Linux servers
Experience with containers (Docker/Podman) and network security
English - B2 or above
Experience building RAG agents/pipelines (retrieval, vector databases, embeddings) - the project has adjacent tasks in this area
Experience with Ollama/OpenWebUI or similar LLM-serving tools
Experience with SSO/MFA integration and role-based access models
German language
Project-based work, fully remote
Priority given to candidates based in Eastern Europe
Compensation: negotiable
Published on: 8/20/2026

DYN-IT
Accelerating growth through AI, n8n & SAP integration at enterprise level.
Please let DYN-IT know you found this job on Wantapply.com. It helps us to get more jobs on our site. Thanks!