Master Thesis: Multimodal Knowledge and Reasoning for Biomedical Safety Applications

Safe Intelligence — this forms the core brand of the Fraunhofer Institute for Cognitive Systems IKS. Connected cognitive systems drive innovation in many sectors, including mobility, healthcare, and automation in industry. Disruptive technologies such as artificial intelligence and quantum computing play a key role here. Fraunhofer IKS is conducting research to ensure that these applications are reliable and verifiably safe. Resilience and intelligence are part of the same process.

In this master thesis, you will work at the intersection of multimodal machine learning, knowledge representation, and reasoning in biomedical safety, contributing to a research system that must reason reliably over heterogeneous data sources.

Scope of Work

• Multimodal data integration: combining structured data (graphs, ontologies, relational databases), unstructured text (scientific literature, clinical reports), and molecular or numerical features into a unified reasoning framework.
• Knowledge‑grounded inference: designing retrieval and reasoning pipelines that ground model output in interpretable, traceable knowledge paths.
• Uncertainty quantification and faithfulness: developing methods to certify when model predictions are well‑supported by evidence and communicating confidence to support human oversight.

You will engage with the full research lifecycle, from literature review and problem formalization to system design, implementation, and empirical evaluation against published baselines, and contribute to an applied research project with real‑world deployment context.

Essential Qualifications

• Strong Python programming skills and good software engineering practices (modular design, version control, documentation).
• Solid foundation in at least one of the following:
• Multimodal learning: experience fusing heterogeneous input types such as text, graphs, structured tables, or molecular representations.
• Knowledge graphs: construction, graph data models, traversal, or graph databases (Neo4j / Cypher ideally).
• Retrieval‑augmented generation (RAG) and LLM integration (LangChain, LlamaIndex, or equivalent).
• Ability to independently read, understand, and synthesize primary research literature.
• Structured, self‑driven working style with attention to reproducibility.

Advantageous

• Graph machine learning: graph neural networks (GNN / GAT / RGCN) or knowledge‑graph embeddings.
• Generative AI knowledge: agentic workflows and multi‑agent systems.

Profile

• Enrolled at a German university; must be able to come to the office in Garching at least one day a week.
• Especially suitable for M.Sc. Computer Science, Bioinformatics, Data Engineering, Computational Life Sciences, or related disciplines.
• Genuine curiosity about trustworthy AI and its application in high‑stakes domains.

What We Offer

• Approachable supervisors and integration into a dynamic interdisciplinary team spanning AI safety, data science, and application domains.
• Hybrid set‑up with workplace at our modern institute building in Garching‑Forschungszentrum, close to TU Munich.
• Hands‑on experience with real‑world data pipelines, HPC infrastructure, and Fraunhofer’s applied research practices.
• Opportunity to work on open scientific questions within an active applied research project, with a clear path toward publication at international venues.

We value and promote the diversity of our employees' skills and therefore welcome all applications – regardless of age, gender, nationality, ethnic and social origin, religion, ideology, disability, sexual orientation and identity. Severely disabled persons are given preference in the event of equal suitability. Our tasks are diverse and adaptable – for applicants with disabilities, we work together to find solutions that best promote their abilities.