Research Associate (E13, ML, IV-317/26)

Improve AI-driven decision support in oncology

About us

The Berlin Institute for the Foundations of Learning and Data (BIFOLD) at TU Berlin (Machine Learning group, Prof. Klaus-Robert Müller) is looking for a research assistant in the field of machine learning for a Junior Research Consortium funded by German ministry of research, technology, and space (”BMFTR”). The sub-project at BIFOLD is led by Dr. Mina Jamshidi Idaji and is carried out in close collaboration with Prof. Philipp Jurmeister at LMU Munich and Prof. Bockmayr at the University Medical Center Hamburg-Eppendorf (UKE), providing access to unique multimodal oncology datasets and expertise in computational pathology
The project focuses on developing novel machine learning methods for multimodal learning in computational pathology. The research aims to integrate diverse biomedical data sources, such as histopathology images, molecular data, and clinical information, to improve AI-driven decision support in oncology. The position combines methodological machine learning research with applications in precision medicine in close collaboration with clinical partners.

Your responsibility

• Conduct original research in machine learning and computational pathology
• Develop, implement, and evaluate novel deep learning methods
• Publish research results at leading machine learning and medical AI conferences and journals
• Collaborate with clinical and interdisciplinary research partners
• Present research at international conferences
• Contribute to open-source software and reproducible research
• Opportunity to pursue a PhD

Your profile

• Successfully completed a university degree (Master, Diplom, or equivalent) in Computer Science, Machine Learning, Mathematics, Electrical Engineering, Computer Engineering, or a closely related field
• Excellent programming skills in Python and strong experience with PyTorch. Experience with scientific computing and reproducible machine learning workflows is expected
• Strong background in machine learning and deep learning, including practical experience with developing, training, and evaluating neural network models
• Solid theoretical foundation in probability, statistics, optimization, and statistical machine learning.
• Good knowledge of German and English (oral and written) required; willingness to acquire the respective missing language skills
• Experience with transformer architectures, foundation models, self-supervised learning, or representation learning is highly desirable
• Previous experience with explainable AI (xAI), uncertainty estimation, causal inference, or interpretable machine learning is an advantage
• Previous experience with biomedical or clinical data, particularly computational pathology, whole-slide images, multi-omics, or medical imaging, is an advantage
• Familiarity with Linux, Git, and high-performance GPU computing is desirable

The listet qualifications should be substantiated by appropriate evidence in the submitted application documents, where applicable.
 

Salary grade: TV-L 13, Berliner Hochschulen
Starting date (Earliest): October 10, 2026
Closing date: Sep 04, 2026
Full job posting: IV-317/26