A fully funded PhD position is available in the Machine Learning and Systems Biology Department at the Max Planck Institute of Biochemistry in Munich, Germany, under the supervision of Prof. Karsten Borgwardt. The research focuses on building clinical foundation models that integrate genomic, clinical, and imaging data to advance real-world healthcare applications and personalized medicine through artificial intelligence. The position is part of the MSCA Doctoral Network (MLCARE), offering international secondments at ETH Zurich and the industry partner Pharmatics. The appointment is for 3 years with a competitive TVöD E13 salary. Applicants must have a Master’s degree (300 ECTS) in Computer Science, Data Science, Physics, Mathematics, Biology, or Medicine, demonstrate excellent English skills, and show motivation for interdisciplinary AI research. Eligibility is restricted to candidates who have not lived or worked in Germany for more than 12 months in the past 36 months. The application window is from January 1 to January 31, 2026. For more information and to apply, visit the provided link or contact Prof. Borgwardt directly.

The Max Planck Institute of Biochemistry (MPIB) in Martinsried, Germany, is seeking a highly motivated PhD student to join the Department of Machine Learning and Systems Biology, led by Prof. Dr. Karsten Borgwardt, for the MLCARE project DC3: Building Clinical Foundation Models for Real-World Healthcare. This project is part of the MSCA Doctoral Network MLCARE, which aims to advance personalized medicine by developing innovative AI solutions that integrate genomic, clinical, and environmental data into comprehensive, multimodal patient representations. The PhD project focuses on developing robust and generalizable clinical foundation models capable of understanding and reasoning across the complex landscape of electronic health records (EHRs). The successful candidate will work on integrating structured data, free-text notes, lab results, and medical imaging to create multi-modal models that accurately reflect real clinical workflows. The research will utilize multi-hospital datasets, including public sources like MIMIC and private clinical data from LMU Hospital, to pretrain models for strong generalization across hospitals and patient populations. The project will employ innovative self-supervised learning strategies to link EHR entries with patient-reported outcomes, reducing the need for extensive manual labeling. A key goal is to develop clinically understandable prompting techniques that enable physicians to interact with these models effectively, minimizing the need for costly fine-tuning and fostering trust in AI-driven medical decisions. The Department of Machine Learning and Systems Biology offers a dynamic, international, and collaborative research environment with a focus on machine learning in medicine, graphs, and protein research. The PhD candidate will benefit from outstanding training opportunities, international secondments at ETH Zurich and with the industrial partner Pharmatics, and access to a strong network of research institutions in the Munich area. The position is fully funded for three years under the MSCA Doctoral Network MLCARE, with salary according to the German public service tariff (TVöD E13). Applicants must have a Bachelor’s and Master’s degree (or equivalent) with at least 300 ECTS credits in relevant fields such as data science, computer science, physics, mathematics, biology, or medicine. Excellent English communication skills are required, and previous research experience in machine learning or computational biology is advantageous. Candidates must not already hold a doctoral degree and must meet mobility requirements (not having resided in Germany for more than 12 months in the past 36 months, with certain exceptions). Applications are accepted only via the online portal during January 1st–31st, 2026, and must include a personal statement, CV, academic records, proof of English proficiency, and at least two letters of recommendation. The Max Planck Society encourages applications from individuals with disabilities and women in research.