PhD Position in Foundation Models for Medical Reasoning
ETH Zürich invites applications for a fully funded PhD position in Foundation Models for Medical Reasoning, hosted by the research group led by Prof. Michael Moor. This opportunity is ideal for ambitious candidates passionate about advancing medical AI and foundation models. The group is at the forefront of developing medical foundation models, agent systems, and reasoning models, aiming to enhance the reliability and faithfulness of medical reasoning across diverse clinical contexts.
The successful candidate will develop novel methods to improve the reasoning capabilities of medical foundation models, including large language models (LLMs), multimodal large language models (MLLMs), and multi-agent systems. Research will involve designing multimodal retrieval-augmentation strategies that integrate electronic health records (EHRs), clinical guidelines, imaging databases, and other structured knowledge sources. The position also focuses on implementing flexible memory and retrieval systems to support reasoning-chain generation and sequential decision-making in clinical tasks, as well as developing approaches to reduce hallucinations and improve adversarial robustness in medical AI systems.
Additional responsibilities include post-training and test-time scaling of multimodal foundation models, co-developing new benchmarks for multimodal clinical reasoning and explainable sequential decision-making, and publishing research results in top-tier machine learning and biomedical venues. The position offers opportunities for collaboration within the MLCARE consortium, including funded secondments to the Max Planck Institute and Siemens, and engagement in open-source contributions and knowledge-transfer activities.
Applicants should hold a Master’s degree in Computer Science, AI, Machine Learning, Mathematics, Electrical Engineering, or a closely related field, or a Master’s degree in Medicine (MD) with strong Python skills and some ML experience. Required skills include strong programming abilities in Python, experience with modern ML stacks (PyTorch, HuggingFace, distributed training), and good computational engineering practices. Experience in LLMs, vision–language models, multimodal learning, or clinical NLP is highly desirable. For computational candidates, experience in large-scale ML training is a strong advantage. Candidates should be able to work independently, contribute to team efforts, and communicate effectively in English. Prior research experience, publications, or industry ML experience are pluses but not mandatory.
The position is fully funded through the MSCA Doctoral Network and offers access to cutting-edge computational resources, including large GPU clusters, and medical and biomedical collaborations. The Department of Biosystems Science and Engineering (D-BSSE) in Basel provides a highly interdisciplinary environment, embedded in a major hub for medical and biomedical research and biotechnology. ETH Zürich is committed to diversity, equality of opportunity, and sustainability, fostering an inclusive and climate-neutral academic community.
To apply, candidates must submit their application online via the ETH Zurich application portal, including CV, Bachelor and Master transcripts, motivation letter, and letters of recommendation (or a list of referees) as a single PDF. Applications via email or postal services will not be considered. As this PhD position is part of the EU-funded MLCARE consortium, applicants should also complete the central application form for the consortium. For further information, contact Prof. Michael Moor's lab at [email protected] (no applications via email).
ETH Zürich is one of the world’s leading universities in science and technology, renowned for its excellent education, cutting-edge research, and global collaborations. The university provides a vibrant environment for independent thinking and academic excellence, with over 30,000 people from more than 120 countries.
