PhD Position in Automated Kinetic Model Generation, Chemical Engineering, Machine Learning, Catalysis Ghent University in Belgium

The Laboratory for Chemical Technology (LCT) at Ghent University is offering a fully funded PhD position focused on automated kinetic model generation for heterogeneous catalytic systems. The research bridges computational chemistry, kinetic modelling, machine learning, and chemoinformatics to accelerate sustainable chemical production processes. The successful candidate will contribute to the development of Genesys, an in-house kinetic model generator, by extending its framework with new reaction families, thermodynamic estimation methods, and kinetic property assignment strategies for heterogeneous catalysis. Integration of machine learning models for predicting thermochemical and kinetic properties, as well as coupling gas-phase and surface-phase mechanism generation, are key aspects of the project.

The PhD candidate will validate developed methodologies on industrially relevant catalyst systems, collaborate with major industrial partners and leading research institutes, and create software tools for the kinetic modeling community. The position offers a competitive tax-free scholarship, extensive UGent benefits, and the opportunity to work with cutting-edge tools in a multidisciplinary environment. Requirements include a master's degree in chemical engineering or a related field, programming experience in Python, knowledge of chemical kinetics and reactor engineering, and proficiency in English (TOEFL > 105 or equivalent). Experience in quantum chemical simulations, machine learning, and software development practices are desirable but not mandatory.

Applications should be submitted via email to [email protected] and [email protected] with the subject line 'Genesys PhD Position Application', including a cover letter, CV, and BSc/MSc transcripts. The position is available from 1 September 2026 (flexible start date). For more information, visit the supervisor's LinkedIn profile or UGent staff pages.