AI Engineer - LLMs and On-Premise AI - Aarhus
Core
Building and deploying production-ready LLM-based solutions and agents in on-premise environments for a Danish public-sector organization.
Role type
Senior AI Engineer (LLMs and On-Premise AI)
Builds
Secure, stable, production-ready LLM services and RAG solutions
Domain
Public sector, Large Language Models, On-premise AI infrastructure
Deliverable
production ML models
Required skills
Python, LLM frameworks, RAG, prompt design, tool calling, structured outputs, Docker, Linux, APIs, CI/CD, model deployment, inference infrastructure
Preferred skills
Model fine-tuning, GPU infrastructure, NLP, regulated environments
Responsibilities
Develop and integrate LLM-based applications and agents; Deploy and operate LLM models in on-premise environments; Build RAG solutions, structured workflows and validation layers; Improve model reliability through guardrails, testing and monitoring; Integrate AI services with existing applications and APIs; Work with sensitive data ensuring security and traceability
Seniority
Senior, hands-on IC
