PhD in Foundation Models and Digital Patient Twins for Precision Medicine at Technical University of Munich
Technical University of Munich / TUM University Hospital is hiring a
PhD student
for research on
foundation models
and
digital patient twins
in
oncology
and
cardiovascular medicine
.
The position is embedded in
TWIN-X
, a
Horizon Europe
consortium with 18 European partners. The project works with large-scale multimodal clinical data, including radiology, pathology, genomics, laboratory values, clinical notes, and longitudinal patient trajectories from several thousand patients.
Research topics include multimodal and longitudinal patient modelling, representation learning, self-supervised and contrastive pretraining, masked modelling, generative objectives, cross-attention models, mixture-of-experts systems, temporal transformers, and JEPA-style models. Own research ideas are strongly encouraged.
The role offers full-time
TV-L E13
funding for
48 months
, access to high-end GPU infrastructure (including H100, H200, and B300 servers), large-scale storage, conference travel, workshops, and short research stays at partner institutions across Europe.
Eligibility highlights: a strong Master's degree in computer science, mathematics, physics, engineering, medical informatics, biomedical engineering, or a related field; excellent quantitative background; strong Python and deep learning skills (preferably PyTorch); and solid foundations in machine learning, statistics, linear algebra, and model evaluation. Excellent English is required; German and prior medical AI experience are helpful but not mandatory.
Supervision is provided in the medical AI environment of TUM University Hospital and the Department of Diagnostic and Interventional Radiology, with Prof. Dr. Lisa Adams, PD Dr. med. Keno Bressem, and Dr. rer. nat. Cosmin I. Bercea involved.
To apply, email your materials to
[email protected]
and include a cover letter, CV, complete Bachelor and Master transcripts, degree certificates, and optional publication/code/reference materials. Applications without complete transcripts cannot be fully assessed.
