Research Assistant

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.

• 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

• 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.

Contact:
Dr. Mina Jamshidi Idaji (mina.jamshidi.idaji@tu-berlin.de)

Please send your application with the reference number and the listet documents (in English) via email to a.gerdes@tu-berlin.de. Official application documents that are not issued in English or German must be accompanied by a translation into either English or German.

• Curriculum Vitae (CV)
• Academic transcripts of B.Sc. and M.Sc. studies
• Contact information for two referees
• A motivation letter (see the required structure below)
• A one-page summary of a research, software, or thesis project that best represents your work. Please clearly describe your own contribution, the main technical challenges, and the outcomes of the project

The motivation letter must be in English and should not exceed one page. Please feel free to include information about the following quesitons in your letter: 1.Why are you interested in this PhD position and its research topic? 2. Which previous experiences and technical skills best prepare you for this position? Please support your answer with concrete examples. 3. What are your expectations for this position? Please describe the type of supervision you are looking for.

By submitting your application via email you consent to having your data electronically processed and saved. Please note that we do not provide a guaranty for the protection of your personal data when submitted as unprotected file. Please find our data protection notice acc. DSGVO (General Data Protection Regulation) at the TU staff department homepage: https://www.abt2-t.tu-berlin.de/menue/themen_a_z/datenschutzerklaerung/.

To ensure equal opportunities between women and men, applications by women with the required qualifications are explicitly desired. Qualified individuals with disabilities will be favored. The TU Berlin values the diversity of its members and is committed to the goals of equal opportunities. Applications from people of all nationalities and with a migration background are very welcome.