Postdoc in Machine Learning for Molecules and Materials

About us

The University of Luxembourg is an international research university with a distinctly multilingual and interdisciplinary character.

The Faculty of Science, Technology and Medicine (FSTM) at the University of Luxembourg contributes multidisciplinary expertise in the fields of Mathematics, Physics, Engineering, Computer Science, Life Sciences and Medicine.
Through its dual mission of teaching and research, the FSTM seeks to generate and disseminate knowledge and train new generations of responsible citizens in order to better understand, explain and advance society and the environment we live in.

Your role

Professor Alexandre Tkatchenko's group at the University of Luxembourg is seeking a postdoctoral researcher to develop machine-learning methods for molecules and materials. Our goal is to take machine learning beyond interatomic potentials: starting from the machine-learning force fields (MLFFs) developed in our group, you will build models that predict the electronic, optical, and transport properties of complex molecular systems and materials directly from their atomic structure, with the long-term goal of foundation models that transfer across chemical space.

We are looking for an early-career scientist with strong method-development skills and the practical ability to build, train, and deploy models at scale. The specific research direction will be shaped together with the successful candidate, building on their strengths and interests and on the group's ongoing projects and international collaborations.

Machine-learning force fields reproduce quantum-mechanical energies and forces at a small fraction of the cost of first-principles methods. Predicting electronic, optical, transport, and dynamical properties remains more challenging because these properties depend on non-local quantum-mechanical response and are sensitive to anharmonic thermal motion, long-range interactions, defects, and interfaces. Accurate reference data are also expensive and scarce. Current first-principles schemes can treat such systems only case by case, at very high computational cost.

Your role will be to close this gap by developing machine-learning methods that predict these properties directly from atomic structure, building on the MLFF architectures developed in our group (e.g., SO3LR model) toward multi-property foundation models. Applications range from molecules and molecular crystals to organic semiconductors, framework materials, and biomolecular systems, where the models are coupled to spectroscopy, charge-transport, and dynamics simulations, often in collaboration with our industrial (e.g., Johnson & Johnson, AstraZeneca, Google) and academic partners.

You will receive scientific guidance from Prof. Tkatchenko and work closely with the group's senior researchers, with support to develop expertise across our complementary research areas. You will also publish your findings and present at international conferences.

Your profile

• A PhD in physics, chemistry, materials science, computer science, or a closely related field
• A track record of method development: you have designed, implemented, and trained new machine-learning models or new simulation methods - not only applied existing ones
• Strong practical skills: proficiency in Python, hands-on experience with a modern ML framework (JAX or PyTorch) and GPU training, and good scientific software-engineering practice, e.g., version control, testing, reproducible workflows
• A solid understanding of quantum mechanics and electronic-structure theory (density functional theory and/or beyond), and familiarity with machine-learning force fields or related atomistic ML models
• Evidence of independent research, demonstrated through publications, open-source code, or both
• Excellent command of English

Desirable:

• Experience with machine learning for electronic structure or spectroscopy, e.g., learned Hamiltonians, densities, excited states, response properties, or with pre-training approaches used in foundation models, multi-task and transfer learning.
• Familiarity with charge-transport theory, electron-phonon or nonadiabatic dynamics, tight-binding models, or excited-state methods
• Experience with molecular dynamics, molecular crystals or organic semiconductors; experience on large HPC systems
  

Applicants are not expected to have expertise in every area listed above. What matters most is a strong foundation in method development, the practical skills to turn ideas into working, scalable code, and the ambition to shape the next generation of machine-learning models for molecules and materials. The successful candidate will receive support to develop complementary skills within the group and through our collaborations.

We offer

• A modern, dynamic university with a personal and inclusive atmosphere. Multilingual and international character. Staff coming from more than 90 countries. Member of The Guild of European Research Intensive Universities
• An exceptional research environment, supported by skilled staff and high-quality equipment. Strong links to professional sectors and the Luxembourg labour market. A unique urban campus with excellent infrastructure
• A partner for society and industry. Cooperation with European institutions, innovative companies, the Financial Centre and a wide range of non-academic partners including ministries, local governments, associations, and NGOs

How to apply

Applications should include:

Early application is highly encouraged, as the applications will be processed upon reception. Please apply ONLINE formally through the HR system. Applications by Email will not be considered.

All qualified individuals are encouraged to apply. In line with our values, the University of Luxembourg promotes an inclusive culture. We encourage applications from individuals of all backgrounds and are dedicated to upholding equality and respect for our employees and students.

General information:

• Contract Type: Fixed Term Contract 12 Month
• Work Hours: Full Time 40.0 Hours per Week
• Location: Belval Campus
• Internal Title: Postdoctoral researcher
• Job Reference: UOL08538

The yearly gross salary for every Postdoctoral Researcher at the UL is EUR 87306 (full time).