CoreShell ML Protein Assembly PDRA (845541)University
FTE: 1.0 FTE (full time)
Contract Type: Fixed term (18 Months)
The Department of Pure and Applied Chemistry is seeking an exceptional and highly motivated Research Associate to join the ARIA-funded CoreShell Fibre Foundry programme.
The programme aims to develop a new approach to manufacturing hollow inorganic fibres using engineered proteins as reusable molecular fabrication units. You will lead the machine-learning component of the computational work package, developing predictive and active-learning approaches to guide the design of protein sequences that assemble into controlled geometries.
You will build and evaluate surrogate models linking protein sequence and molecular-simulation descriptors to experimentally observed assembly outcomes. These models will be used to prioritise candidate protein sequences for simulation and experimental testing and will be refined through iterative design build-test cycles.
Working within an interdisciplinary team of computational chemists, protein scientists and engineers, you will:
Develop machine-learning and active-learning models for predictive protein-assembly design
Define suitable molecular descriptors, input features and prediction targets
Analyse sequence, simulation and experimental datasets
Prioritise candidate protein sequences for simulation and experimental validation
Develop robust, documented and reproducible Python workflows
Communicate model outputs clearly to computational and experimental collaborators
Contribute to project meetings, milestone reports, publications, presentations and research-data management.
You will have a PhD in computational chemistry, chemical physics, molecular modelling, bioinformatics, machine learning, computational biology, materials informatics or a closely related discipline. You will also have experience developing and evaluating machine-learning models, strong Python and scientific-computing skills, and the ability to work both independently and as part of a collaborative research team.
Experience of active learning, Bayesian optimisation, uncertainty quantification, surrogate modelling, protein or peptide design, molecular descriptors, sequence-based modelling or moleculardynamics data would be advantageous.
The post is full time and fixed term from 1 October 2026 until 29 February 2028. Any continuation beyond this initial funded period would be subject to successful passage of the programme milestone gate, the release of further funding and separate University approval.
Initial interviews have been scheduled for 21/09/2026
Informal enquiries may be directed to Professor Tell Tuttle, Programme Lead, at [email protected]