MPL performance in FCs: insights and optimization from ML powered ab-initio simulations

Required:

Candidates must have:

1/ a strong background in atomistic simulations with experience in at least one of

• Classical Molecular Dynamics simulations using e.g., Lammps, Gromacs, ...
• Ab initio simulations (e.g. Density Functional Theory, …) using e.g. Abinit, QuantumEspresso, Vasp, Turbomole, Gaussian, ...

2/ excellent programming skills in Python (examples from, e.g. personal projects on git repositories, will be considered as a plus in the evaluation),

3/ expertise in machine learning techniques and knowledge of the most standard tools for machine learning (e.g., Scikit-Learn, TensorFlow, Pytorch, ...),

4/ experience with Unix/Linux systems and experience in using high-performance computing centers,

5/ excellent knowledge of written and spoken English (working language).

Nice to have:

Candidates should possess:

1/ knowledge and experience in best practices in continuous integration/continuous deployment,

2/ knowledge and experience in constructing and/or using machine-learned interatomic potentials,

3/ knowledge and experience in using and/or developing workflows with e.g., Fireworks + jobflow + atomate2, ASR, …

4/ knowledge and experience in using and/or developing materials science or chemistry python packages, e.g., pymatgen, ASE, RDKit, …

5/ knowledge and experience in using databases (SQL or noSQL).

The selected candidate will receive a salary in accordance with the MSCA regulations for DCs. The gross salary includes a living allowance (€3400 per month subject to MSCA Country Correction Coefficient, namely 100% for Belgium and 81,6% for Greece), a mobility allowance (€600 per month) and a family allowance (€660 per month), if the researcher has family (‘Family’ means persons linked to the researcher by (i) marriage or (ii) a relationship with equivalent status to a marriage recognized by the legislation of the country where this relationship was formalized or (iii) dependent children who are actually being maintained by the researcher). The guaranteed (EC) funding is for 36 months.

Applicants can be of any nationality and must hold a Master of Science degree (or equivalent) in Engineering, relevant to the aforementioned topics. They need to fully respect the following eligibility criteria:

(a) Must be doctoral candidates, i.e., not already in possession of a doctoral degree at the date of the recruitment.

(b) Must undertake transnational mobility. Researchers must not have resided or carried out their main activity (work, studies, etc.) in Belgium for more than 12 months within the 36 months immediately before their date of recruitment. Compulsory national service, short stays such as holidays, and time spent as part of a procedure for obtaining refugee status under the Geneva Convention are not taken into account.

The candidates should send a CV, cover letter, BSc and MSc degrees (certified copies plus translation in English), examples of your coding in python packages (e.g., github/gitlab links) and two letters of recommendation. Copies of publications could be sent later on, upon request. Personal interviews might be asked.

All applications must be mailed to both david.waroquiers@matgenix.com  and frudakis@uoc.gr with subject: “BLESSED-DC13-Application”.

The outcome of the evaluation process will be announced by end of July 2023. The contract is expected to start on the 1^st of September 2023.

During the first 18-months period, DC13 will be working at the R&D Division of Matgenix in Charleroi, Belgium. Within a team with a strong expertise in computational materials science and chemistry, workflow automation and machine-learning, DC13 will have the opportunity to learn, develop and apply state-of-the-art techniques for high-throughput simulations as well as specific machine learning models tailored to materials and chemistry. This will provide a step stone for the benefit of the BLESSED project.

The second 18-month period DC13 will be working in the Computational Chemistry group of Chemistry Department of the University of Crete. Taking advantage of and using the strong expertise of the group in various fields of computational chemistry and materials science (ab-initio quantum chemistry techniques, Monte Carlo and Molecular Dynamic simulations together with Machine Learning etc.) for the benefit of the project BLESSED is expected. The UoC provides an HPC computing environment which is available for use in connection with process modeling of the project.