Creating knowledge. Making a difference. Shaping the future. This is what the University of Münster stands for as one of the strongest research-oriented universities in Germany and one of the largest employers in the region. Every day, over 7,000 employees devote themselves to cutting-edge research and excellent teaching. We share more than a workplace. We share the desire to make a real impact – regionally and internationally. Our day-to-day work is distinguished by diversity, openness and space to pursue one’s ideas. Become a part of our team – in academia, a technical or manual trade, or administration.
The Computer Vision and Machine Learning Research Group at the Institute for Geoinformatics at the University of Münster is seeking to fill the following position:

Postdoctoral Research Associate (Wissenschaftlicher Mitarbeiterin, salary level E 13 TV-L)

**for the BMFTR-funded Junior Scientist Research Centre ‘ReproTrack.MS’ at the earliest possible date (e.g., starting December 2026 for the second funding period). We are offering a fixed-term full-time position (100%) for 3 years.

The position is located in the research group of Prof. Benjamin Risse and focuses on the development of computer vision, machine learning, and explainable AI methods for the analysis and characterisation of sperm motility. The project is carried out jointly with the Centre for Reproductive Medicine and Andrology (CeRA) and aims to advance the imaging and analysis of visual biomedical data by exploiting state-of-the-art imaging technologies while developing advanced deep learning-based computer vision algorithms.

Project Description

The project focuses on developing and applying novel machine learning-driven computer vision approaches for high-throughput, quantitative sperm-motility analysis. In particular, you will develop advanced algorithms for object tracking, semantic segmentation, feature extraction, and explainable analysis of large-scale time-lapse videomicroscopy datasets. A central goal of this interdisciplinary project is to develop tailored tracking algorithms and AI-based bottom-up approaches to quantify sperm-motility patterns, enabling early diagnosis of fertility disorders, and to investigate the biophysical and genetic determinants of sperm locomotion by correlating motion phenotypes with flagellar mechanics and multi-omics data.**

Your tasks:

• Developing tailored machine learning and computer vision (AI) strategies to characterise sperm motility and assess male fertility
• Implementing deep learning-based tracking and segmentation methods for large-scale time lapse videomicroscopy datasets
• Adapting foundation models, prompt-based tracking methods, and transformer architectures to analyze complex, high-resolution ciliary and flagellar beating patterns
• Investigating and correlating multimodal (clinical, physical, and genetic) datasets to enable advanced screening based on locomotion features and underlying genetics (such as CatSper channel function)
• Integrating explainable AI (XAI) strategies to validate and interpret model predictions for clinical diagnostics
• Collaborating closely with biomedical researchers, imaging experts, and clinicians within an interdisciplinary research team involving experts from medicine, biology, physics, and computer science

Our expectations:

• A completed doctorate (PhD) in Computer Science, Mathematics, Physics, Geoinformatics, Engineering, or a related quantitative field
• Demonstrated experience in machine learning, deep learning, computer vision, and biomedical image or video analysis
• Experience with tracking algorithms, semantic segmentation, or motion feature extraction is highly desirable
• Sound theoretical knowledge in the field of deep neural network optimisation, training, and transformer architectures
• Very good programming skills in Python and deep learning frameworks such as PyTorch and/or TensorFlow
• Willingness to work in a highly interdisciplinary project combining artificial intelligence, biophysics, and reproductive medicine
• Excellent English communication skills (spoken and written); German skills are advantageou

Additionally desirable are

• Experience in building small hardware prototypes such as camera systems and basic microscopic optics
• Demonstrated knowledge of explainable AI (XAI) or other deep learning-related techniques relevant for complex image/video analysis
• Knowledge of biophysical modelling, hydrodynamic simulations, or statistical analysis of flagellar trajectorie

Advantages for you:

• The opportunity to work at the cutting edge of AI, computer vision, and translational biomedical imaging
• A highly interdisciplinary project combining artificial intelligence, advanced microscopy, biophysics, and reproductive health research
• Access to unique biomedical imaging datasets and close collaboration with experimental research groups and core facilities
• Competitive, international, and collaborative research environment
• Structured career development and broad professional development opportunities within the ReproTrack.MS framework
• Salary according to tariff agreement, extra annual payment, and company pension plan (VBL
• A respectful and appreciative work environment within a diverse tea

The University of Münster strongly supports . We welcome all applicants regardless of sex, nationality, ethnic or social background, religion or worldview, disability, age, sexual orientation or gender identity. We are committed to creating family-friendly working conditions. Part-time options are generally available.

We actively encourage applications by women. Women with equivalent qualifications and academic achievements will be preferentially considered unless these are outweighed by reasons which necessitate the selection of another candidate.

For inquiries, please contact: Prof. Benjamin Risse, , +49 251 83 32717

Are you interested? Then we look forward to receiving your application by 2026-09-15.

Please send us your application electronically in PDF format including:

• Letter of motivation (max 2 pages)
• Curriculum vitae and academic CV
• Transcript and scanned copies of your degree certificates (PhD and Master's)
• Two letters of recommendation and/or names and contact details of two references

Please note that we cannot consider other file formats.

Reference number: 2026_08_07