A Doctoral Researcher (PhD student) in Machine Learning for Electron–Phonon Interactions and Wannier-Based Hamiltonians
Core
Develop data-driven machine learning workflows to predict Wannier Hamiltonians, phonon properties, and electron–phonon coupling in layered transition-metal dichalcogenides for thermoelectric transport and gas sensor applications.
Role type
Doctoral Researcher (PhD student) in Machine Learning for Electron–Phonon Interactions
Builds
Machine learning framework linking electron–phonon interactions, Wannier-based Hamiltonians, and phonon properties for functional materials
Domain
Computational chemistry, materials science, and machine learning
Deliverable
production ML models
Required skills
Python programming, atomistic simulations, electron–phonon physics, machine learning, scientific method and software development
Preferred skills
Electronic structure software (Quantum ESPRESSO), molecular dynamics packages (LAMMPS), machine learning interatomic potentials (GAP, MACE, NequIP), ML libraries (Scikit-learn, TensorFlow, PyTorch, e3nn_jax), Boltzmann transport solvers, phonon codes (Phono3py, ShengBTE)
Technologies
Quantum ESPRESSO, Wannier90, EPW, CSC's Puhti, Mahti, LUMI, e3nn_jax
Responsibilities
Generate datasets from electronic structure theory calculations; apply E(3)-equivariant AI framework to quantify band-convergence effects and model gas adsorption effects; manage large-scale simulations on supercomputing facilities; share results with experimental collaborators
Seniority
PhD student, early-career researcher