PhD Position in Biomedical Signal Processing and Machine Learning Wearable Physiological Mo

Materials science and technology are our passion. With our cutting‑edge research, Empa's around 1,100 employees make essential contributions to the well‑being of society for a future worth living. Empa is a research institution of the ETH Domain.

Develop data processing pipelines for multimodal physiological signals (pre‑processing, feature extraction, and data fusion) from wearable sensing systems.

Design and validate machine learning models for predictive monitoring of physiological states.

Analyse large experimental datasets and quantify sensor performance (accuracy, robustness, signal integrity) under varying physiological and environmental conditions.

Conduct statistical evaluation and model validation using controlled measurements and sensing‑dummy reference data.

Collaborate with project partners and disseminate results through reports, visualisations, and scientific publications.

You hold an M.Sc. in Data Science, Computer Science, Engineering, Physics, Statistics or a related field and are motivated to apply advanced analytics to real-world digital health challenges. You have strong foundations in signal processing and are confident working in Python or MATLAB (e.g. Num Py, Pandas, Sci Py). Experience with biomedical signals or signal quality assessment is an advantage.

• You bring initial experience in machine learning (e.g. scikit‑learn, XGBoost, PyTorch) and statistical modelling (e.g. mixed models, ANOVA, power analysis). Curiosity and a willingness to learn are a pre‑requisite and familiarity with physiological data (e.g., heart rate variability) is a plus.
• You enjoy working with complex, multimodal datasets and developing robust algorithms for continuous monitoring and predictive modelling. You are comfortable combining coding, data analysis, and experimental validation in lab and field settings.
• You work independently, think analytically, and take initiative.
• Excellent English skills are required;
  German is a plus.