Generative AI-enabled Molecular Design for Optoelectronic Applications
This is a fully-funded 4-year PhD position based in the HetSys Centre for Doctoral Training at the University of Warwick.
Project outline
Molecular optoelectronic devices have a high potential in ultrasensitive detection, nanoscale electronics, and medical imaging, but finding promising molecules for these applications is challenging because exceptional optical and electronic performance needs to be balanced with stability and ease of synthesis.
Current AI tools can explore vast chemical spaces but often suggest molecules that are unstable or hard to make. This project develops a generative AI framework that utilizes machine learning predictions and quantum chemistry simulations to design stable, synthesizable, high-performance molecules.
The framework will integrate multi-objective optimisation and multi-fidelity active learning, creating a practical route to discovering new molecules for optoelectronic devices.
Supervisors
Primary: Dr Zsuzsanna Koczor-Benda
(Chemistry)
Dr Albert Bartók-Pártay (Engineering/Physics)
Project Partner: Unviersity of Birmingham
This project aims to develop an efficient closed-loop optimisation framework that combines generative search in chemical space with validation through computational modelling. It will explore multi-objective optimisation approaches to balance trade-offs between optoelectronic performance, stability, and synthetic accessibility, building on discussions with experimental collaborators.
The project introduces multi-fidelity active learning that combines low-cost ML surrogates for rapid screening, ML interatomic potentials/tight-binding calculations for intermediate validation, and selective high-level density functional theory calculations for in-depth characterisation.
The outcome will be a modular, extensible, high-performance computing-ready software platform for generative molecular optimisation, enabling a wide range of follow-up projects in molecular optoelectronics design and providing transferable methodologies for other molecular design challenges as well.
The project will deliver generated molecular datasets with associated properties and uncertainties, providing valuable information and potential candidates for molecular optoelectronics applications, which can be tested by experimental collaborators. The work will be published in high-profile journals and disseminated at international conferences.
You will acquire skills in programming (Python), high-performance computing, molecular screening and design, generative AI, scientific machine learning, a wide range of computational and quantum chemistry modelling techniques, optimisation methods, database handling and analysis.
You will also develop collaborative, project management, presentation and writing skills.
These skills position you for careers in AI research, computational materials science, national laboratories, tech industry or academic research. The HetSys training provides a foundation for these skills through dedicated courses and cohort activities.
We require at least a II(i) honours degree at BSc or an integrated masters degree (e.g. MPhys, MChem, MSci, MEng etc.) in a physical sciences, mathematics or engineering discipline. We do not accept applications from existing PhD holders.
If you are an overseas candidate please check here that you hold the equivalent grades before applying.
For postgraduate study in HetSys, the term “overseas” or “international” student refers to anyone who does not qualify for UK home fee status. This includes applicants from the European Union (EU), European Economic Area (EEA), and Switzerland, unless they hold settled or pre-settled status under the UK’s EU Settlement Scheme.
If you are a European applicant without UK residency or immigration status that qualifies you for home fees, you will be classified as an overseas student.