En poursuivant votre navigation sur ce site, vous acceptez le dépôt de cookies dans votre navigateur. (En savoir plus)
Portail > Offres > Offre UPR8011-JULLAM-002 - H/F Postdoc 2ans Machine-learning pour la simulation atomistique

M/F Postdoc 2y Machine-learning for atomistic simulations

This offer is available in the following languages:
Français - Anglais

Date Limite Candidature : jeudi 12 août 2021

Assurez-vous que votre profil candidat soit correctement renseigné avant de postuler. Les informations de votre profil complètent celles associées à chaque candidature. Afin d’augmenter votre visibilité sur notre Portail Emploi et ainsi permettre aux recruteurs de consulter votre profil candidat, vous avez la possibilité de déposer votre CV dans notre CVThèque en un clic !

Faites connaître cette offre !

General information

Reference : UPR8011-JULLAM-002
Workplace : TOULOUSE
Date of publication : Thursday, July 22, 2021
Type of Contract : FTC Scientist
Contract Period : 24 months
Expected date of employment : 1 November 2021
Proportion of work : Full time
Remuneration : 2648
Desired level of education : PhD
Experience required : 1 to 4 years


Machine-learning interaction potentials (MLIP) have been recently proposed to bridge
the gap between quantum accurate calculations and fast empirical modeling. In this project, we will use a machine-learning method that we are currently developing and that is named Physical LassoLars Interaction Potential (PLIP). In particular, the retained candidate will work on two fundamental improvements for PLIP. He/she will implement an on-the-fly training of the potential which will unlock transferability issues that are often observed in machine-learning potential. Then, he/she will tackle the challenges related to long-range interactions by explicitly incorporating electrostatic effects with machine-learned Coulombic charges.


- Hands-on PLIP method
- Implement on-the-fly training
- Include electrostatic charges
- Test method on different materials


- CPP coding
- Molecular dynamics LAMMPS
- Force field construction
- Machine-learning

Work Context

The work will be carried out in the group SINanO of CEMES located in Toulouse. The hired candidate will be supervised by Julien Lam in collaboration with Magali Benoit and Rémi Arras.

We talk about it on Twitter!