PhD Candidate: ML for Electron–Phonon Physics & TMDCs

Euraxess; Espoo; On-site; EUR 30,132 - 40,176; Full time

Benefits offered by this job

Occupational healthcare

Right to study in doctoral programme

Salary according to Finnish university

Research environment access

Job summary

Aalto University is seeking a Doctoral Researcher (PhD student) in Machine Learning for Electron–Phonon Interactions and Wannier-Based Hamiltonians. You will develop data-driven ML workflows, generate datasets from electronic structure calculations, and apply advanced AI frameworks to analyze thermoelectric transport and gas adsorption effects.

Join the ELPH-ML project and collaborate with experts in chemistry, physics, and materials science.

Qualifications

• Master's degree in Chemistry, Physics, Materials Science, Mathematics, Computer Science, or a related field.
• Prior programming experience, especially Python.
• Strong interest in atomistic simulations, machine learning and software development.
• Proficiency in English (written and spoken).

Responsibilities

• Develop data-driven and machine learning workflows to predict Wannier Hamiltonians, phonon properties, and electron–phonon coupling.
• Generate datasets from electronic structure calculations using Quantum ESPRESSO, Wannier90, and EPW.
• Apply the E(3)-equivariant AI framework to quantify band-convergence effects on thermoelectric transport and model gas adsorption effects.
• Manage large-scale simulations on supercomputing facilities and share results with experimental collaborators.

Skills

Python programming

English proficiency

Machine learning in materials science

Atomistic simulations

Data analytics

Education

Master’s degree in Chemistry/Physics/Materials Science/Math/CS or related field

Tools

Python

Quantum ESPRESSO

TensorFlow / PyTorch

Scikit-learn

e3nn_jax

Job description

Aalto University is seeking a Doctoral Researcher (PhD student) in Machine Learning for Electron–Phonon Interactions and Wannier-Based Hamiltonians. You will develop data-driven ML workflows, generate datasets from electronic structure calculations, and apply advanced AI frameworks to analyze thermoelectric transport and gas adsorption effects.

Join the ELPH-ML project and collaborate with experts in chemistry, physics, and materials science.