AI/ML-Powered Digital Twin Frameworks for Biopharmaceutical Processes University College Dublin in Ireland

This PhD project at University College Dublin (UCD), School of Chemical & Bioprocess Engineering, focuses on developing AI/ML-powered, physics-informed digital twin frameworks for biopharmaceutical processes. The research aims to create computational methodologies that integrate mechanistic and first-principles knowledge with data-driven models, enabling digital twins that reduce reality gaps and support continuous learning in biomanufacturing. Candidates will have the opportunity to specialize in either upstream or downstream biopharmaceutical processing, contributing to the digitalization and optimization of bioprocesses.

The ideal candidate should hold an MSc in chemical/(bio)process engineering, AI/ML, systems engineering, or a related field. Experience with Python and machine learning frameworks is expected, while prior knowledge in biomanufacturing technologies is advantageous but not essential. The project is well-suited for candidates passionate about advancing digital bioprocessing and applying computational tools to real-world biomanufacturing challenges.

The position offers a 4-year structured PhD program, including a monthly stipend and a dedicated research budget to support attendance at international conferences and workshops, as well as relevant research expenses and equipment. The research will be supervised by Dr. Sebastián Espinel Ríos, who can be contacted for further information and application submission.

Interested applicants should prepare a single PDF containing their CV, academic transcripts, and a letter of motivation, and email it to Dr. Espinel Ríos at [email protected]. The application deadline is July 1, 2026. For more details, visit the project page on FindAPhD.

This opportunity is ideal for those seeking to work at the intersection of biotechnology, artificial intelligence, machine learning, bioengineering, chemical engineering, control systems, cybernetics, systems engineering, mathematical modelling, and stochastic processes. The project is fully funded, providing financial support and resources for research and professional development.