PhD Student Positions (f/m/d)

The Data-Driven Materials Design group at the INM – Leibniz Institute for New Materials in Saarbrücken invites applications for several

PhD student positions (f/m/d).

The group, led by Prof. Viktor Zaverkin, is part of a joint research environment including the INM – Leibniz Institute for New Materials, the Faculty of Mathematics and Computer Science at Saarland University, and the German Research Center for Artificial Intelligence (DFKI).

Its research focuses on the development of machine learning methods for modelling molecules and materials, enabling accurate prediction of their properties across length and time scales. The research covers several directions, ranging from the development of machine-learned interatomic potentials (including atomistic foundation models) to active learning strategies for efficient data generation and data-driven approaches for accelerating atomistic simulations.

The group is embedded in an interdisciplinary research environment combining experimental groups in materials science, chemistry, synthetic biology and biophysics with machine learning and close connections to research at University Campus.

Possible research topics

Depending on the candidate’s interests and background, the PhD project may involve one or more of the following directions:

• Machine-learned interatomic potentials, including atomistic foundation models
• Active learning and data generation strategies for atomistic modelling and beyond
• Data-driven acceleration of atomistic simulations
• Machine learning methods for direct prediction of molecular and materials properties
• Generative models for molecular and materials design

The exact research topic will be defined together with the successful candidates based on their interests and expertise.

Applicants are asked to briefly describe in their motivation letter which research directions they are particularly interested in and why.

Your tasks

• Conduct independent research in data-driven materials design
• Develop and implement novel machine learning methods
• Apply these methods to molecular and materials systems
• Contribute to scientific publications and conference presentations
• Collaborate with researchers from materials science, chemistry, and machine learning

Your profile

• Master’s degree in computer science, applied mathematics, physics, chemistry, materials science, or a related field
• Background in at least one of the following areas: machine learning, computational chemistry or materials science, atomistic simulations, or scientific computing
• Background in scientific programming (e.g., Python, PyTorch, or similar tools)
• Interest in developing machine learning methods for modeling molecules and materials
• Ability to work independently and collaboratively in an interdisciplinary research environment
• Excellent written and spoken English

We offer

• An interdisciplinary and international research environment working on cutting-edge problems in data-driven materials design
• Access to modern computational infrastructure
• Opportunities to publish research in leading scientific journals and present it at international conferences
• The chance to help shape a newly established research group
• A high degree of scientific freedom in shaping the research project
• Employment according to the German public service salary scale

Please submit your application via our online application portal, including a motivation letter, CV, relevant certificates, and the names of 1–2 references as a single PDF file (max. 10 MB). Applications will be reviewed continuously until the positions are filled.

The INM practices an open and appreciative corporate culture in which the existing diversity is promoted and lived. The institute is an equal opportunity employer with a certified family-friendly policy, and it provides offers for a better work-life balance, flextime, and mobile working. We promote professional opportunities for women and strongly encourage them to apply. People with disabilities are expressly encouraged to apply and will be given priority if equally qualified.