Postdoctoral Researcher

Your position

The successful candidate will be responsible for designing and implementing the predictive modeling strategy of the project.

This includes:

• Developing machine-learning prediction models for individual-level risk prediction using heterogeneous data (psychological and biological profiles, ecological momentary assessment (EMA), and time series sensing data)
• Applying, evaluating, and comparing supervised and unsupervised methods (e.g., regularized regression, tree-based models, ensemble methods, clustering, dimensionality reduction) and deep learning approaches
• Developing and applying explainable AI (XAI) methods to ensure interpretability and to gain insights from the data
• Translating predictive models into algorithmic “advising” or warning frameworks, balancing accuracy, interpretability, and scalability
• Collaborating closely with psychologists, physiologists, and other heat domain experts to ensure that models align with theoretical constructs and applications
• Leading and co-authoring high-quality scientific publications
• Designing and contributing to open, reproducible, and well-documented research pipelines and code bases

Your profile

We are looking for a postdoctoral researcher who is methodologically strong and motivated to work at the intersection of applied machine learning, social sciences, and natural sciences.

Essential qualifications:

• A completed PhD in data science, computer science, statistics, computational social science, economics, quantitative psychology, or a closely related field
• Expertise using machine learning
• Ability to work with high-dimensional and/or longitudinal data
• Excellent critical programming skills in Python
• Strong command of English (spoken and written)
• Familiarity with ethical and responsible AI considerations
• Interest in translating models into applied or decision-support tools

Other desirable qualifications:

• Experience in harmonizing different types of datasets
• Experience with explainable AI or interpretable machine-learning methods
• Experience with psychological questionnaire data and/or biological measurement data
• Comprehension of the German language