The Theory Group in the Chemistry Department at École normale supérieure - PSL, led by Guillaume Stirnemann and Damien Laage, is recruiting for two PhD student positions and one postdoctoral researcher in the field of AI and theoretical chemistry. The group focuses on leveraging artificial intelligence and machine learning to enhance the statistical accuracy of molecular simulations of chemical reactions, aiming for quantum-level precision. Their research addresses unique challenges in chemistry, such as efficient generation of training datasets, complex reaction mechanisms, excited-state chemistry, and hybrid ML/MM approaches. The group is dynamic and collaborative, with around 10 students working at the intersection of chemistry, physics, and data science. Recent successes include applications of neural-network-based molecular dynamics and the development of frameworks like ArcaNN for automated training set generation in reactive molecular simulations. Representative research includes studies on proton transport mechanisms in water and the use of machine-learning interatomic potentials for chemical reactivity. Applicants should have a strong background in theoretical chemistry, with additional experience in statistical mechanics and/or machine learning highly valued. The positions offer the opportunity to contribute to cutting-edge research in AI-driven molecular simulations, with potential applications in quantum chemistry, reaction kinetics, and materials science. The group is based at École normale supérieure in Paris, France, and is affiliated with CNRS and PSL University. While specific funding details are not provided, these are standard PhD and postdoctoral positions in France. Interested candidates are encouraged to contact the supervisors directly for more information and application procedures. For further details, see the provided LinkedIn and publication links.

The group at École normale supérieure (PSL Research University) in Paris, France, led by Guillaume Stirnemann, is offering several Master's thesis opportunities for 5-6 months starting in January or February 2026. The research topics include machine-learned interatomic potentials for chemical reactivity with applications to electrocatalytic reduction of carbon dioxide (in collaboration with Damien Laage), prebiotic chemistry (with A. Marco Saitta), generative AI and chemical reactivity (with Marylou Gabrié and Damien Laage), and the effect of hydrostatic pressure on lipid and protein dynamics in GPCR systems (with Jérôme Hénin). These projects are highly interdisciplinary, combining theoretical chemistry, computational chemistry, machine learning, artificial intelligence, biophysics, and molecular dynamics. Candidates must be enrolled in a Master's program or equivalent and have a strong academic record in physics, chemistry, computer science, or related fields. Some positions have secured funding, while others will seek funding, and all may be extended into PhD opportunities upon mutual agreement. Interested students are encouraged to contact the group for further details and to apply. The environment is collaborative, with opportunities to work alongside leading researchers in the field.