• Harmonise and curate longitudinal digital phenotyping
  datasets
• Support feature engineering from EMA, actigraphy, and
  GPS-derived data
• Contribute to the evaluation of generative models and
  simulation outputs
• Develop and apply resilience metrics to simulated and
  empirical trajectories
• Contribute to the identification and interpretation of
  different transition patterns
• Assist in the preparation of analysis pipelines, documentation, and reproducible workflows
• Contribute to scientific publications, conference
  presentations, and team activities
• Pursue an independent doctoral project within the
  thematic framework of the research group

• Very good university degree (Master’s or equivalent) in
  psychology, neuroscience, computational psychiatry,
  cognitive science, data science, computer science,
  statistics, or a related field
• Strong interest in mental health research, longitudinal
  data, and computational approaches
• First experience with quantitative methods and
  programming, ideally in Python and/or R
• Interest in machine learning, time-series analysis, digital phenotyping, or computational modelling
• Motivation to work in an interdisciplinary and collaborative environment
• A careful, structured, and self-motivated working style
• Very good written and spoken English; German is
  welcome but not required

• The opportunity to pursue a PhD in an innovative and
  internationally connected research environment
• Close supervision and integration into an interdisciplinary team at the interface of psychiatry and data science
• Access to high-quality longitudinal datasets and modern computational methods
• Opportunities for publication, conference participation, and methodological training

We are looking to support a newly established research group as soon as possible. The position is embedded in the third-party funded research project SiReD-MH (Tipping Minds: Simulation of Resilience Dynamics in Mental Health). The project develops a hybrid in-silico framework to better understand how resilience changes over time and how transitions into mental illness may emerge in young people at risk. The work is based on longitudinal digital phenotyping data and combines data-drivenmodelling, simulation, and clinically relevant interpretation.
The doctoral researc her will contribute to the empirical and analytical backbone of the project and will develop an independent PhD project within this broader framework.