Postdoctoral Position in Language Models for Pediatric Data Analysis at ETH Zurich ETH Zurich in Switzerland

ETH Zurich is seeking a highly motivated postdoctoral researcher to join the Medical AI Lab in a collaborative project with the University Children's Hospital Basel. The position focuses on the development, validation, and safe integration of large language models (LLMs) for automated coding of pediatric diagnoses from electronic health records (EHRs). The goal is to enhance research capabilities and clinical data usability in pediatric healthcare settings.

The successful candidate will lead research on adapting and developing locally hosted language models for diagnostic coding tasks, including rigorous model validation and safe deployment. The role involves publishing research results in top-tier venues, collaborating closely with clinicians, clinical coders, and hospital IT infrastructure, and contributing to the vibrant AI community at ETH Zurich and SwissAI initiative.

Applicants must have a PhD in a relevant field such as Computer Science, Medical AI, or Medical Informatics, with strong programming skills in Python and experience with modern ML/AI/LLM stacks (e.g., PyTorch, HuggingFace, distributed training). Proficiency in German at C1 level or higher is required for analyzing local patient records. Prior experience with LLMs, clinical NLP, RAG, vector databases, and medical data coding (ICD-10) is highly desirable. Familiarity with Docker, server environments, GPU infrastructure, and good computational engineering practices is expected. Candidates should be able to work independently, contribute to team efforts, and communicate effectively in English and German.

The position is full-time and fixed-term, based at the Department of Biosystems Science and Engineering (D-BSSE) in Basel. The project offers access to cutting-edge computational resources, including large GPU clusters, and opportunities for clinical collaboration. ETH Zurich is committed to diversity, equality of opportunity, and sustainability, providing an inclusive and supportive environment for all staff and students.

To apply, candidates should submit their application through the ETH Zurich online application portal, including a CV, Bachelor and Master transcripts, motivation letter, and letters of recommendation or a list of referees. Applications via email or postal services will not be considered. For further information, candidates may contact Prof. Michael Moor's lab email (no applications via email).