The Public Policy Group at ETH Zurich invites applications for a research assistant in quantitative social science for a project using machine learning to improve refugee resettlement.
The position is part of an innovative project using machine learning and matching algorithms to improve the resettlement process for refugees and asylum seekers. We are developing GeoMatch , a recommendation tool to assist governments in identifying communities where newly arriving refugees are most likely to thrive. This tool is currently being tested in the field in Switzerland and the United States, with an imminent launch in the Netherlands. The project is a collaborative effort between ETH Zurich and Stanford University.
Job descriptionYour task will be to support the ongoing project in the Netherlands. Your role will include cleaning and processing data from our partner agencies, training and fine-tuning machine learning models to predict refugee resettlement outcomes, and conducting simulations and backtests to assess model performance and estimate the tool's real-world impact. You will have regular check-ins with the project team at Stanford but will conduct the day-to-day data work yourself.
Profile - Enrolled in a master's program at a Swiss university / ETH with a strong focus on data science (data science, computer science, economics, social sciences, etc.)
- Experience programming in R
- Demonstrated problem-solving ability
- Proficiency in data cleaning and management and experience working with complex datasets
- Reliable, structured and precise working style
- Strong communication skills regarding technical matters and data analysis
- Comfortable formulating questions and proactively seeking guidance as needed
- Curious and self-motivated, with a strong sense of ownership over their work
- Fluency in English, oral and written
- Familiarity with supervised machine learning (e.g. gbm, xgboost, etc.) is an advantage.
We offerHands-on experience on an empirical research project that aims to provide tangible social impact for refugees
Diverse activities:
- Training and assessing machine learning models
- Managing, cleaning, and processing complex, real-world datasets
- Evaluating the effectiveness of algorithmic matching strategies on refugee outcomes
- Conducting simulated backtests to estimate the performance of the GeoMatch tool in a new policy context
- Highly collaborative work environment: you will be working closely together with the project team at Stanford University
- Professional supervision by experienced researchers, supporting you in your career development as a data scientist / applied econometrician / quantitative social scientist
- Salary and pension benefits according to ETH regulation
The position is secured for 6 months starting September/October 2025.
> Working, teaching and research at ETH Zurich
We value diversity In line with our values , ETH Zurich encourages an inclusive culture. We promote equality of opportunity, value diversity and nurture a working and learning environment in which the rights and dignity of all our staff and students are respected. Visit our Equal Opportunities and Diversity website to find out how we ensure a fair and open environment that allows everyone to grow and flourish.
