Postdoctoral Research Associate (f/m/d) EU Research Project TWIN-X, 100%, TV-L

MyTUM-Portal
Technische Universität München

Postdoctoral Research Associate (f/m/d) EU Research Project TWIN-X, 100%, TV-L- E14

17.03.2026, Wissenschaftliches Personal

Postdoctoral Research Associate (f/m/d)
EU Research Project TWIN-X
Full-time (100%)

Fixed-term: 48 months
The Project TWIN-X (Digital Twins with Generative AI for Explainable Precision Medicine) is a European Commission-funded research project under Horizon Europe (HORIZON-HLTH-2025-TOOL-05-03). The consortium comprises 18 partners from 12 European countries. TWIN-X builds comprehensive digital patient twins by fusing multimodal clinical data (radiology, pathology, genomics, lab values, clinical notes) into unified, explainable vector representations for clinical decision support in oncology and cardiovascular medicine.
Duration: 48 months

Coordinator: TUM (PD Dr. Keno Bressem)
Your Responsibilities

• Development and implementation of generative AI models (in particular diffusion models and variational approaches) for creating explainable patient representations
• Research on multimodal representation learning for fusing heterogeneous clinical data (imaging, pathology, genomics, clinical text) into unified vector representations
• Design and evaluation of methods for anomaly detection and disease recognition based on learned normative representations
• Development of vision-language models for clinical reasoning and interpretable reporting of medical imaging data
• Creation of benchmarks and evaluation frameworks for the systematic assessment of generative models in a clinical context
• Supervision of doctoral researchers and master students within the project
• Supporting the project coordinator in the scientific steering of the EU collaborative project, including preparation of deliverables, periodic reports, and consortium meetings
• Scientific communication with international consortium partners and representation of the project at conferences
  Your Profile
• Completed doctoral degree (Dr. / Ph.D.) in Computer Science, Medical Informatics, Biomedical Imaging, Machine Learning, or a related field
• Demonstrated research experience in generative models for medical imaging (e.g., diffusion models, VAEs, GANs)
• Publications in high-ranking journals and conferences (e.g., Nature portfolio, MICCAI, NeurIPS, ICML, CVPR/WACV)
• Experience with multimodal representation learning and/or vision-language models in a medical context
• Strong programming skills in Python and common deep learning frameworks (PyTorch)
• Excellent communication skills in English (German is a plus)
• Independent, structured working style and experience in supervising students
  Preferred:
• Experience with anomaly detection and normative representation learning in medical imaging
• Experience with federated learning or privacy-preserving AI methods
• Experience organizing scientific workshops or community engagement (e.g., MICCAI, ICML)
• Experience with EU research projects or other third-party funded projects
• Experience with clinical data and/or interdisciplinary collaboration with clinicians
• US or EU patents in the field of machine learning / computer vision
  We Offer
  o Remuneration according to TV-L E14 (100%)
  o Fixed-term position for the project duration (48 months)
  o Central role in a top-ranked EU research project (15/15 score) with an international consortium
  o Integration into a dynamic, interdisciplinary research environment at the intersection of AI and clinical medicine
  o Access to TUM and Klinikum rechts der Isar infrastructure and resources
  o Flexible working hours and the option for remote work
  o Opportunity for habilitation
  Application
  Please send your complete application documents (cover letter, CV, list of publications, certificates, references) by email to:

PD Dr. med. Keno Bressem keno.bressemtum.de TUM is committed to increasing the proportion of women in its workforce. Applications from women are therefore expressly encouraged. Candidates with disabilities who are otherwise equally qualified will be given preference

Die Stelle ist für die Besetzung mit schwerbehinderten Menschen geeignet. Schwerbehinderte Bewerberinnen und Bewerber werden bei ansonsten im wesentlichen gleicher Eignung, Befähigung und fachlicher Leistung bevorzugt eingestellt.

Hinweis zum Datenschutz:
Im Rahmen Ihrer Bewerbung um eine Stelle an der Technischen Universität München (TUM) übermitteln Sie personenbezogene Daten. Beachten Sie bitte hierzu unsere Datenschutzhinweise gemäß Art. 13 Datenschutz-Grundverordnung (DSGVO) zur Erhebung und Verarbeitung von personenbezogenen Daten im Rahmen Ihrer Bewerbung. Durch die Übermittlung Ihrer Bewerbung bestätigen Sie, dass Sie die Datenschutzhinweise der TUM zur Kenntnis genommen haben.

Kontakt: keno.bressemtum.de