Postdoc: AI for Clinical Decision Support Systems

Aalborg University; Aalborg; On-site; DKK 420,000 - 540,000; Full time

Benefits offered by this job

Danish language courses

Collaborative research environment

Job summary

Aalborg University’s Center for Clinical Data Science (CLINDA) invites applications for a full-time postdoctoral researcher to develop AI-based systems for clinical decision support in hospitals. The two-year position may be extended, starting December 1, 2026, in Aalborg, Denmark.

The role focuses on building an interactive framework using large language models and retrieval-augmented generation to ground reasoning in real-world clinical data.

Qualifications

• PhD required for appointment as postdoc.
• Experience in machine learning and NLP is highly desirable.
• Health data science or related health field is a plus.
• Strong Python programming skills to prototype ideas.
• Solid mathematical foundation for algorithms and systems.
• Excellent communication and collaboration with clinical experts.
• English fluency; Danish or Scandinavian language is a plus but not required.

Responsibilities

• Develop AI agent framework using LLMs and retrieval-augmented generation (RAG).
• Synthesize multi-modal data for clinical decision support.
• Collaborate with clinical partners and hospitals in the North Denmark Region.
• Incorporate human-in-the-loop (HITL) to ground reasoning in clinical evidence.
• Explore forecasting and multi-step simulations across patient data.

Skills

PhD in CS or related field

ML/NLP experience

Python programming

Mathematical foundations

English fluency

Team collaboration

Danish knowledge a plus

Education

PhD in Computer Science or related field

Tools

Python

Job description

Aalborg University’s Center for Clinical Data Science (CLINDA) invites applications for a full-time postdoctoral researcher to develop AI-based systems for clinical decision support in hospitals. The two-year position may be extended, starting December 1, 2026, in Aalborg, Denmark.

The role focuses on building an interactive framework using large language models and retrieval-augmented generation to ground reasoning in real-world clinical data.