Doktorand (PhD-Student) im Bereich Machine Learning für Elektron-Phonon-Wechselwirkungen und Wannier-basierte Hamiltonoperatoren (m/w/d)

Job Description

The Department of Chemistry and Materials Science is looking for a Doctoral Researcher (PhD student) in Machine Learning for Electron-Phonon Interactions and Wannier-Based Hamiltonians

The ELPH-ML project, led by Dr. Ransell D'Souza at the Department of Chemistry and Materials Science, Aalto University, and the Data-driven Atomistic Simulation (DAS) group, led by Prof. Miguel Caro at the Department of Chemistry and Materials Science, Aalto University, are jointly hiring a Doctoral Researcher. In this position, you will work on a project funded by the Research Council of Finland to build a machine learning framework linking electron-phonon interactions, Wannier-based Hamiltonians, and phonon properties for functional materials. You will work under the supervision of the Principal Investigator, Dr. Ransell D'Souza, and collaborate closely with Prof. Miguel Caro's group, whose core expertise is the development of machine-learning-infused atomistic modeling techniques and their application to important problems in chemistry, physics and materials science. Together, you will help advance a key scientific discipline that directly impacts important technological and societal topics such as thermoelectric energy harvesting and next-generation gas sensors. The project has access to state-of-the-art supercomputing facilities (CSC's Puhti, Mahti, and LUMI) and is well integrated within the international electronic-structure and machine learning communities. Informal inquiries about the position can be directed to Ransell D'Souza ([email protected]). Please read the description below in full before directly contacting us by email.

Your role and goals

You will develop data-driven and machine learning workflows to predict Wannier Hamiltonians, phonon properties, and electron-phonon coupling in layered transition-metal dichalcogenides (TMDCs) such as MoS₂, WS₂, MoSe₂, WSe₂, and WTe₂. For training the machine learning models, you will generate datasets from electronic structure theory calculations using Quantum ESPRESSO, Wannier90, and EPW. You will apply the developed E(3)-equivariant AI framework to quantify band-convergence effects on thermoelectric transport (Seebeck coefficient, conductivity, ZT) and to model gas adsorption effects (NH₃, CO, CO₂) relevant to next-generation 2D gas sensors. You will manage large-scale simulations run on world-class supercomputing facilities alongside AI algorithms and data analytics tools, and share your results with experimental collaborators. The position is part of the Research Council of Finland project ELPH-ML (https://research.fi/en/results/funding/88752). In combination with academic development courses at Aalto University, we will help you grow a competitive and international career profile.

Your experience and ambitions

We welcome candidates with a Master's degree in (computational) chemistry, physics, or materials science who are curious about applied machine learning in the natural sciences. Prior machine learning or Python experience is a strong bonus, but not a must. We seek colleagues who enjoy coding, scripting and analytics, and are keen to push the boundaries of data-driven materials science and machine learning in atomistic simulations. This project requires creative thinking and programming, as well as technical expertise in materials simulations, electron-phonon physics, and machine learning. We further appreciate willingness to travel, teach and mentor, collaborate and communicate science.

To succeed in this role, you should have

• A Master's degree (or equivalent) in Chemistry, Physics, Materials Science, Mathematics, Computer Science, or a related field. (You are required to have a degree that would allow you to enroll for a PhD program in the granting institution, e.g., a 1st hons BSc in the UK is also eligible.)
• Prior programming experience, especially with Python. While you are not expected to be an expert programmer, some hands-on experience in programming is mandatory. Note that it will be entirely possible to develop more advanced programming skills during the doctoral studies.
• A strong interest in atomistic simulations, machine learning and scientific method and software development.
• Proficiency in English (written and spoken).

(Preferred) Experience with any of the following:

• Electronic structure software (e.g., Quantum ESPRESSO).
• Molecular dynamics packages (e.g., LAMMPS).
• Machine learning interatomic potentials (e.g., GAP, MACE, NequIP ).
• Machine learning libraries and frameworks such as Scikit-learn, TensorFlow, or PyTorch, and e3nn_jax.
• If you have experience with other types of modeling tools (e.g., Boltzmann transport solvers, phonon codes like Phono3py/ShengBTE), please state it in your cover letter.

Applicants must fulfill the eligibility and admission criteria for Aalto's Doctoral Programme in Chemical Engineering as specified at Aalto Doctoral Programme in Chemical Engineering | Aalto University.

If you feel you are interested and qualified for the position but are concerned about not fulfilling all the criteria, still feel free to apply. Take a look at this article in Forbes.

What we offer

Aalto's Department of Chemistry and Materials Science is a leading research environment in Finland for computational chemistry and materials science, with four groups specializing in different branches (Soft Materials Modelling, Computational Chemistry, Inorganic Materials Modelling, and Data-driven Atomistic Simulation).

The fixed term contract is initially for 2 years and during the first 6 months you must apply and receive a right to study in the doctoral programme. Aalto University follows the salary system of Finnish universities. The starting salary for Doctoral Researchers is 3142,65€ / month (gross). The contract includes Aalto University occupational healthcare benefits.

The position will be filled as soon as a suitable candidate is identified. The starting date for the position is in the autumn 2026, but the exact date can be agreed with the selected candidate. The primary workplace will be the Otaniemi Campus at Aalto University.

Ready to apply?

To apply for the position, please submit your application no later than 31.08.2026 including the attachments mentioned below as one single PDF document in English through the link 'Apply now' link at the bottom of the web page.

Please note: Aalto University's employees should apply for the position via our internal HR system Workday (Internal Jobs) by using their existing Workday user account (not via the external webpage for open positions). If you are a student or visitor at Aalto University, please apply with your personal email address (not aalto.fi) via Aalto University open positions.

• Letter of motivation (max 1 page): Include your name and email. Briefly motivate your interest in the position and explain how/to what extent you fulfill the requirements. Briefly mention any prior research experience you may have. Please, do not use ChatGPT or similar tools to prepare your cover letter for you.
• CV including list of publications (max 2 pages): personal and academic information, list of skills, projects, etc. Lying on your CV is immediate grounds for disqualification. If you are invited for an interview, you will be asked about information provided here. If you are eventually offered the position, you will be asked for a transcript of academic records.
• Contact details of at least two referees (or letters of recommendation, if already available)

Applications sent via email will not be considered; only submissions through the online recruitment system are accepted.

Questions about the vacancy may be directed via email to Dr. Ransell D'Souza [email protected] or Prof. Miguel Caro [email protected] . Please contact primarily project PI, D'Souza. Contact Prof. Caro only if Dr. D'Souza can't be reached.