Research Assistant (Doctoral student) project "Multi-fidelity, active learning strategies for exciton transfer in cryptophyte antenna complexes"

Bergische Universität Wuppertal

RESPONSIBILITIES AND DUTIES

• Interdisciplinary work at the interface of computer science and mathematics with applications in the context of molecular machine learning, within the thematic scope of the project “Multi-fidelity, active learning strategies for exciton transfer in cryptophyte antenna complexes” of the DFG Priority Programme “Molecular Machine Learning”
• Development of novel machine learning methods for modeling molecular properties, in particular regression models for bi-molecular properties.
• Collaboration in an international team working on related research questions in machine learning, uncertainty quantification, and high-performance computing with applications in the natural and engineering sciences.
• Teaching responsibilities (equivalent to 4 contact hours per week) and supervision of student research and thesis projects

PROFESSIONAL AND PERSONAL REQUIREMENTS

• Completed academic university degree (Master’s or equivalent) in a relevant discipline (e.g., computer science, mathematics, physics, data science)
• Strong analytical skills in the context of machine learning and/or (numerical) mathematics
• Excellent knowledge of a programming language (preferably Python or C/C++)
• Interest in developing novel bivariate methods in machine learning for molecular property prediction within a relevant interdisciplinary application
• Ideally, experience with multipole methods, low-rank or tensor approximations
• Good command of English (working language within the team, international collaboration)
• A competent, proactive personality with commitment and motivation
• Ability to work independently and enjoyment of teaching
• Successful completion of a scientific programming task within the thematic context of the advertised position. Full details on the programming task can be found at https://www.hpc.uni-wuppertal.de/de/peter-zaspel/challenge-in-bi-molecular-machine-learning/