Job Opportunity: Scientific Assistant at the Biomedical Data Science (BMDS) Lab
The Biomedical Data Science (BMDS) Lab is dedicated to exploring data-driven solutions for healthcare applications, particularly concerning neurological conditions such as spinal cord injury (SCI), lower back pain, neurodegenerative disorders, and neurological tumors. Our research thrives on collaboration across various disciplines, harnessing expertise in medicine, biology, and computer and data science. We are currently seeking a Scientific Assistant to join our growing team and contribute to our interdisciplinary research partnerships. The anticipated start date for this position is March 1, 2026.
About the Project
Traumatic spinal cord injury (SCI) poses profound, lifelong consequences for affected individuals and their families. A significant challenge in predicting long-term recovery lies in the substantial heterogeneity of patient outcomes, which traditional clinical assessments may not fully capture. Standard neurological evaluations alone cannot reflect the underlying biological and functional diversity, thus limiting both prediction accuracy and treatment effectiveness. This project aims to bridge this gap by integrating neurological assessments with neurophysiological measurements and routine blood biomarkers. Leveraging advanced machine learning techniques, we seek to combine these diverse data sources to identify the most informative clinical features, ultimately providing more accurate and interpretable recovery predictions. This innovative approach aims to support better patient stratification, prognosis, and personalized treatment strategies.
Key Responsibilities
- Data Exploration and Management: Work with international datasets of SCI patient data, ensuring accurate handling, preprocessing, and integration of heterogeneous clinical, neurophysiological, and biomarker information. These datasets will be readily available at the project's onset.
- Model Development: Design and implement an advanced multi-branch neural network capable of integrating various data modalities into a unified representation.
- Multi-task Learning Framework: Build and evaluate models to predict multiple interrelated recovery outcomes simultaneously, leveraging shared information to enhance predictive performance, interpretability, and generalization.
Qualifications
- A Master’s degree in Computer Science, Data Science, Biomedical Engineering, or a related field.
- Strong Python programming skills with a proven track record of developing and training machine and deep learning models using Keras/TensorFlow and/or PyTorch, supported by experience in statistical data analysis.
- Experience with collaborative coding practices, version control (e.g., Git), and working on computing clusters.
- Familiarity with SCI data or related research topics is advantageous.
- A background in biomedical projects and experience in interdisciplinary collaboration is a plus.
- Motivated to work within a diverse team and committed to scientific excellence.
- Proficient in both written and spoken English.
What We Offer
- A one-year project-based contract with an 80% workload at the BMDS Lab.
- A stimulating, collaborative environment within ETH Zurich, one of the world’s leading universities in science and technology.
- The opportunity to contribute to groundbreaking biomedical data science with direct clinical relevance.
- Professional development of your skills in data science, machine learning, and neuroinformatics, focused on critical health conditions, especially SCI.
- Integration within a highly motivated, multidisciplinary, and collaborative team.
- Opportunities to learn from field experts and contribute to an active research lab.
Apply online using the form below. Only applications matching the job profile will be considered.
For more information about the BMDS lab, please visit our website.
If you have any questions regarding the position, please direct them to Dr. Olga Taran via email at olga.taran@hest.ethz.ch (please note that applications sent to this address will not be considered).