Postdoctoral Fellow (f/m/x) in Modeling & AI in Neuro-Cognitive Aging

This role is designed as a career accelerator for researchers who aim to combine academic excellence with skills that are highly relevant both in leading academic environments and in the growing AI–Health–Tech sector. You will work with state-of-the-art infrastructure, including 7T MRI, connectomics, and high-performance computing, while being embedded in a strong international research network with close collaborations with institutions such as UCL, Oxford, and Max Planck Institutes. Close mentorship and structured career support, including guidance on independent funding applications (e.g. ERC, DFG, BMBF), are provided. Researchers have access to large-scale, high-quality datasets, the DZNE’s ten-site network, and the CRC 1436, within an active international research environment. Dedicated funding supports participation in international conferences.

In this position, you will contribute to advancing how individual differences in neuro-cognitive aging and dementia are modeled and understood. Your tasks include:

• Developing and implementing novel disease progression models, including latent multimodal dynamics and state-space approaches.
• Applying uncertainty-aware regression methods, using parametric and non-parametric techniques, to characterize disease trajectories and deviations from healthy aging.
• Integrating Deep Learning approaches with Bayesian inference and latent variable models.
• Analyzing high-dimensional, multimodal data such as MRI, FLAIR, cognitive assessments, and fluid biomarkers.
• Contributing to high-impact scientific publications and presenting findings at international conferences.
• Collaborating closely within an interdisciplinary team across neuroscience, psychology, medicine, and data science.
• Mentoring junior researchers and supporting a constructive, collegial team culture.

We welcome applications from researchers with diverse academic backgrounds and career paths.

• A completed PhD in Machine Learning, Computational Neuroscience, Quantitative Psychology, Physics, Applied Mathematics, or a closely related field, or equivalent research experience.
• A strong foundation in multivariate statistics and modeling, for example in regression, Bayesian inference, representation learning, or generative models.
• Experience with Python and common machine learning or statistical frameworks such as PyTorch, TensorFlow, Stan, scikit-learn, or comparable tools.
• An interest in interdisciplinary research and openness to working across disciplinary boundaries, including psychology and medicine.
• Fluency in written and spoken English
• Motivation to further develop an independent research profile, either with a long-term perspective in academia or in applied research and industry.