The Data Integration in the Life Sciences group, led by Prof. Dr. Katharina Baum, is seeking a motivated student assistant to contribute to the cutting-edge, BMBF-funded research project Act-i-ML (Methods for Active Informed Machine Learning). This project is a close collaboration with the Hasso Plattner Institute. We are developing and improving machine learning methods by integrating domain knowledge from Ordinary Differential Equations (ODEs) with active learning strategies. The goal is to make ML models more flexible, efficient, and reliable, especially when working with limited data. Detailed information can be found on our group website: https://www.mi.fu-berlin.de/w/DILIS/WebHome

Job description:
As a student assistant, you will play a crucial role in the software development lifecycle of the novel methods created within our research group. Your primary tasks will include:
- Assisting in the research taking place in our group.
- Collaborating with our researchers to translate new algorithms into high-quality, reusable Python software packages.
- Engaging in the full software engineering process, including refactoring, comprehensive testing to ensure code reliability, and creating clear documentation.
- Supporting the team in preparing and implementing various informed machine learning models for benchmarking and analysis.

Desirable:
- Currently enrolled in a Bachelor's or Master's program in Computer Science, IT Systems Engineering, Data Science, Bioinformatics, Mathematics, Physics, or a related field.
- Solid, demonstrable software engineering skills and ability to write clean, testable, and well-documented code.
- A foundational knowledge of machine learning concepts.
- Experience with Python and its scientific computing/ML libraries.
- Very good command of English (B2)
- Exposure to ordinary differential equations (desired).

For further information, please contact Umur Kaya (u.kaya@fu-berlin.de / +493083853401).