Curriculum Vitae
About me
Python developer and data scientist with a PhD in computer science and experience in machine learning, signal processing, time-series data, and scientific software. Developed and validated algorithms for raw sensor data, built open-source Python tools, and worked on automated testing, performance optimisation, and reproducible data analysis. Combines strong technical expertise with experience in interdisciplinary research, project coordination, and student supervision.
Technical skills
Programming: Python, C++, Cython, SQL
Data and machine learning: NumPy, pandas, scikit‑learn, tensorflow/keras, pytorch, statsmodels, R, lme4, mgcv, docker
Software development: Git, Linux, Github Actions, automated testing, code reviews, agile development, open source
Professional Experience
- 2021 - 2025: PhD Research fellow @ UiT The arctic university of Norway
- Developed methods for measuring sleep, sedentary behaviour, and physical activity from raw data collected by hip‑worn accelerometers under free‑living conditions.
- Developed an algorithm for automatically detecting time in bed from raw hip‑worn acceleration data, enabling continuous assessment of sleep and sedentary behaviour from hip‑based sensor data.
- Investigated how sensor auto‑calibration and algorithm selection affect estimates of moderate‑to‑vigorous physical activity and sedentary behaviour.
- Made analysis methods and software available as open source.
- Worked on data processing, algorithm development, statistical analysis, validation, and reproducible research.
- Coordinated research activities and contributed to project planning and funding applications.
- Supervised students and contributed to the academic guidance of student projects.
- 2016 - 2019 Python and ML Developer (25% position) @ University in Tübingen
- Migrated and further developed scientific software from C++ to Python.
- Optimised runtime through Cython, parallelisation, and algorithmic improvements.
- Developed, trained, and evaluated machine‑learning models for various quantitative linguistics tasks.
- Implemented new features and integration tests based on project requirements.
- Wrote technical documentation and contributed to the maintenance and further development of the codebase.
- 2014 - 2018 Teaching asstistant (25% stilling) @ University of Tübingen
- Taught and supervised students in programming, algorithms, computer science, and experimental methods.
- Led exercise groups and laboratory sessions in undergraduate computer science and cognitive science courses.
- Designed exercises, assessed submissions, and provided specific academic feedback.
- Served as a point of contact between students and lecturers and assisted with the administration of examinations.
Education
- 2025 PhD in Computer Science @ University of Tromsø
- Dissertation: Device‑based measurement of lifestyle‑related variables from the hip – Methods for 24 h wear protocols under free‑living conditions (url)
- The work involved algorithm development, signal processing, machine learning, and the development of open‑source software for measuring sleep, sedentary behaviour, and physical activity from hip‑worn accelerometers
- 2020 M.Sc. in Cognitive Science @ University of Tübingen
- 2017 B.Sc. in Cognitive Science @ University of Tübingen
Selected software projects
- Physical Activity Analysis Toolbox (PAAT) (Github, ReadTheDocs, Article)
- Developed and maintain a Python package for analysing raw accelerometer data.
- Implements algorithms for sleep, sedentary behaviour, and physical activity, with automated testing and continuous integration.
- The software has been published in the Journal of Open Source Software.
- Technologies: Python, NumPy, pandas, TensorFlow/Keras, Git, GitHub Actions, and automated testing
- Pyndl: Naive discriminative learning in python. (Github, ReadTheDocs, Article)
- Contributor and maintainer
- Further developed a Python package for analysing large text corpora.
- Improved runtime and resource usage through Cython and algorithm optimisation, and contributed automated tests and new functionality.
- Technologies: Python, Cython, automated testing, Git, and code reviews.
- Fachschaftsempfänger (Github, Website)
- Developed a data-integration application that collects information from several sources and publishes content to a digital information display.
- The application has been in continuous operation since 2018.
- Technologies: Python, Django, ELT, system integration, RestAPI, data retrieval, and Git.
Selected Publications
Weitz, M., Syed, S., & Horsch, A. (2025). PAAT: Physical Activity Analysis Toolbox for the analysis of hip-worn raw accelerometer data in Python. Journal of Open Source Software, 10(111), 8136. https://doi.org/10.21105/joss.08136
Hammer, T. M., Johansson, J., Emaus, N., Furberg, A.-S., Gracia-Marco, L., Morseth, B., Nilsen, O. A., Ubago-Guisado, E., Vlachopoulos, D., Weitz, M., Evensen, E., & Christoffersen, T. (2025). Changes in accelerometer-measured physical activity and self-reported leisure time physical activity from adolescence to young adulthood: A longitudinal cohort study from the Fit Futures Study. International Journal of Behavioral Nutrition and Physical Activity, 22(1), 99. https://doi.org/10.1186/s12966-025-01799-4
Weitz M., Syed S., Hopstock L. A., Morseth B., Henriksen A., & Horsch, A. (2025) Automatic time in bed detection from hip-worn accelerometers for large epidemiological studies: The Tromsø Study. PLOS ONE 20(5): e0321558. https://doi.org/10.1371/journal.pone.0321558
Weitz, M., Morseth, B., Hopstock, L. A., & Horsch, A. (2024). Influence of Accelerometer Calibration on the Estimation of Objectively Measured Physical Activity: The Tromsø Study. Journal for the Measurement of Physical Behaviour, 7(1). https://doi.org/10.1123/jmpb.2023-0019
Sering, K., Weitz, M., Shafaei-Bajestan, E., & Künstle, D. E. (2022). Pyndl: Naive discriminative learning in python. Journal of Open Source Software, 7(80), 4515. https://doi.org/10.21105/joss.04515