PhD student (m/f/d) | Building Clinical Foundation Models for Real-World Healthcare Full-time

PhD Student (M/F/D) | Building Clinical Foundation Models for Real-World Healthcare

The Max Planck Institute of Biochemistry (MPIB) in Martinsried is one of the world's leading research institutions in the fields of biochemistry, cell and structural biology, and biomedical research. With approximately 30 scientific departments and research groups and about 680 employees, the MPIB is one of the largest institutes of the Max Planck Society.

The Department of Machine Learning and Systems Biology led by Prof. Dr. Karsten Borgwardt is looking to recruit a highly-motivated PhD student (m/f/d) for the project Building Clinical Foundation Models for Real-World Healthcare (MLCARE project DC3). The position is funded by the MSCA Doctoral Network MLCARE (Machine Learning Computational Advancements for peRsonalized mEdicine). The MLCARE Doctoral Network seeks to advance personalized medicine by developing cutting-edge AI solutions that integrate genomic, clinical, and environmental data into holistic, multimodal patient representations. The program will equip doctoral candidates with the technical, analytical, and ethical skills needed to lead the future of patient-centered, AI-driven medicine.

The advertised PhD project aims to develop robust and generalizable clinical foundation models (FMs) that can understand and reason across the diverse and often messy landscape of electronic health records (EHRs). By integrating structured data, free-text notes, lab results, and medical imaging, the PhD researcher will create multi-modal models that reflect the full richness of real clinical workflows. Using multi-hospital datasets, including both public sources such as MIMIC and private clinical data from LMU Hospital, the models will be pretrained to achieve strong generalization across hospitals and patient populations. Innovative self-supervised learning strategies will link EHR entries with patient-reported outcomes, enabling the models to learn without extensive manual labelling. To ensure practical impact, the project will focus on creating clinically understandable prompting techniques that help physicians interact with these models more effectively–avoiding costly fine-tuning and building trust in AI-driven medical decisions.

Qualifications

Applicants must hold a Bachelor's degree and a Master's degree (or equivalent) with a minimum total of 300 ECTS credits in fields such as data science, computer science, physics, or mathematics. Candidates with background in biology and medicine, as well as mathematical, computational, and engineering disciplines are also encouraged to apply. They should be enthusiastic about developing new methods in machine learning to solve problems in the life sciences. Excellent interdisciplinary communication skills as well as written and oral command of the English language are essential. Previous research experience in machine learning and computational biology is advantageous but not required.

Specific Requirements

• Applicants must not already be in possession of a doctoral degree at the time of recruitment. Researchers who have successfully defended their doctoral thesis but have not yet been formally awarded the degree are not considered doctoral candidates.
• Enrollment in a doctoral programme at time of recruitment leading to the award of a degree in at least one EU Member State or Horizon Europe associated country.
• Full-time and exclusive dedication to the assigned MSCA project.
• Candidates may not have resided or carried out their main activity (work, studies, etc.) in Germany for more than 12 months in the 36 months immediately before the recruitment date – unless as part of a compulsory national service or a procedure for obtaining refugee status under the Geneva Convention.

Research Environment

An MSCA Doctoral Network is a competitively selected joint doctoral programme, implemented by partnerships of universities, research institutions, research infrastructures, businesses (including SMEs), and other socio-economic actors from different countries across Europe and beyond. The programme leverages complementary competences of the participating organizations and enables sharing of knowledge, networking activities, the organization of workshops and conferences. Doctoral candidates in particular benefit from outstanding training opportunities and international secondments.

The doctoral candidate recruited for MLCARE project DC3 will be located in the Department of Machine Learning and Systems Biology at the Max Planck Institute of Biochemistry in Martinsried, near Munich, with the opportunity to undertake secondments at ETHZ and with an industrial partner (Pharmatics). The Department of Machine Learning and Systems Biology is an international, enthusiastic, and collaborative team in an outstanding dynamic scientific environment. Research foci in the department are machine learning on graphs, machine learning in medicine and machine learning in protein research. The Max Planck Institute of Biochemistry was founded in 1973 with the aim to understand fundamental mechanisms of biochemistry, cell and structural biology, biophysics and molecular medicine. Machine learning and bioinformatics play an increasingly important role in this endeavor. The institute is part of a strong network of research institutions in the southwest of Munich and provides outstanding research opportunities for its scientists.

Payment will be according to qualifications and in accordance with TVöD E13 (German public service tariff contracts, more information on the salary scales of PhDs in Germany can be found here). The initial appointment will be for 3 years. Informal inquiries are welcome and should be sent to borgwardt@biochem.mpg.de. Further information about the institute and the department.

The Max-Planck Society is committed to increasing the number of individuals with disabilities in its workforce and therefore encourages applications from such qualified individuals. Furthermore, the Max Planck Society seeks to increase the number of women in research and explicitly encourages women to apply.

Application

Then please upload your complete application documents, containing a one-page letter with a personal statement describing your scientific accomplishments and your interests in our department and its research, a detailed CV, academic records, a proof of English proficiency in electronic form via the online application website and arrange for at least two letters of recommendation to be sent to borgwardt-office@biochem.mpg.de by the application deadline with subject [Application DC3 – your name and surname]. In addition, it is important to fill in the the central application form, indicating your preference for project DC3. Only complete applications will be considered.

Application window: May 1st – 29th, 2026. Applications will be reviewed on a rolling basis.

Applications by e-mail will not be considered for data protection reasons. Candidates may apply to more than one position within the MLCARE doctoral network, if relevant.