Research Collaborator - Machine-learning exchange-correlation functionals for electronic-structure calculations (Open)
jm.pitarke@ehu.eus
We are currently accepting applications for the above mentioned position. This is a unique opportunity for junior researchers with a recent PhD degree in Physics or related fields to join one of DIPC’s high-profile research teams.
The role
The successful candidate will develop machine-learned exchange-correlation (xc) functionals for density-functional theory (DFT). The approach is non-empirical and data-driven: the models are trained on large databases of reference data for model and real systems rather than fitted to experimental or molecular benchmark data. Our goal is to develop a universal enhancement factor suitable for a wide range of electron densities, making it applicable to a broad range of materials and atomic environments. This enhancement factor aims to improve upon traditional analytical forms, which contain only a handful of parameters and are designed to satisfy exact constraints.
The research will include:
- Construction of a dataset of enhancement factors from electronic-structure calculations of real materials.
- Training of machine-learning models for the meta-GGA enhancement factor, using this dataset and the Python library JAX.
- Assessment of the training set’s coverage through comparison with existing materials databases (e.g. the Materials Project).
- Evaluation of the model’s accuracy in predicting energies and/or thermodynamic properties of condensed-matter systems, such as crystalline solids or liquid water.
- Interfacing of the JAX-based model with widely used DFT codes, such as Quantum ESPRESSO or SIESTA.
- Time permitting, extension of the formalism beyond meta-GGA.
Desired background & competences
Requirements:
The successful candidate will have a PhD in Physics, Materials Science, Chemistry, or a related field, as well as:
- Experience gained during the PhD in electronic-structure calculations (e.g. DFT or RPA) or atomistic simulations (e.g. molecular dynamics or Monte Carlo).
- Proficiency in Python.
- Experience with high-performance computing resources.
- Proficiency in spoken and written English.
Desirable skills:
The following will be considered an asset:
- Experience in the development of electronic-structure methods.
- Experience in the development of machine-learning methods for atomistic simulations or electronic-structure calculations.
- Experience with one or more of the libraries JAX, PyTorch or TensorFlow.
- Programming experience in Fortran or C++.
- A strong publication record.
Working conditions
- Estimated annual gross salary: Salary is commensurate with qualifications and consistent with our pay scales
- Target start date: 2027/01/01
We provide a highly stimulating research environment, and unique professional career development opportunities.
We offer and promote a diverse and inclusive environment and welcomes applicants regardless of age, disability, gender, nationality, ethnicity, religion, sexual orientation or gender identity.
The center
About the team
The research will be conducted under the supervision of Prof. José M. Pitarke, in close collaboration with Dr. Pablo Piaggi's team at nanoGUNE's theory group, specializing in the application of machine learning to atomistic simulations and with access to excellent high-performance computing (HPC) resources, including their own servers and large European supercomputers equipped with state-of-the-art graphics processing units (GPUs) for artificial-intelligence applications.
How to apply
Interested candidates should submit an updated CV and a brief statement of interest to the following application email below.
Names and contact details of at least two referees.
The reference of the specific opening to which the candidate is applying should be stated in the subject line, and the application must be received before the application deadline.
Although candidates are welcome to contact the project supervisors to know further details about the proposed research activity, please be aware that the application will be evaluated only if it is submitted directly to the email address listed below as application email.
- Reference: 2026/60
- Application deadline: 2026/12/17
- Application email: jobs.research@dipc.org
Selection process
Applications received by the deadline will be evaluated by a Committee designed by the DIPC board on the basis of the following criteria:
- CV of the candidate (40%)
- Adequacy of the candidate’s scientific background to the project (40%)
- Reference letters (10%)
- Other: Diversity in gender, race, nationality, etc. (10%)
Evaluation results will be communicated to the candidates soon after. Positions will only be filled if qualified candidates are found.
The DIPC may revoke its decision if the candidate fails to join by the appointed time, in which case the position will be awarded to the candidate with the next highest score, provided it is above 50 (out of 100).
However, the selected candidate may keep the position if, in the opinion of the Selection Committee, the candidate duly justifies the reasons why he or she cannot join before the specified deadline, and as long as the project allows it.
Ayuda CEX2024-001491-S financiada por MIU/AEI/10.13039/501100011033

