PhD Studentship in Bayesian Optimisation Considering Late-Stage Process Design
UCL - Department of Chemical Engineering
Qualification Type:PhDLocation:LondonFunding for:UK Students, EU Students, International StudentsFunding amount:circa £23,805 per annum + UK feesHours:Full TimePlaced On:13th March 2026Closes:31st May 2026
Stipend: circa £23,805 per annum + UK fees
Duration of Studentship: 4 years
Start date: October 2026
Vacancy information
The Department of Chemical Engineering at the University College London (UCL) invites applications for a fully funded 4-year PhD program in Process Systems Engineering.
The project aims at integrating data-driven optimisation and design of experiments techniques with model-based process optimisation using hybrid strategies.
Funding for this project covers the home tuition fees and a stipend.
Studentship description
In the chemical and process industry, the standard progression through technology readiness levels often fixes key process and design parameters at early stages, and revising these parameters is either not considered or ruled out for cost reasons. Still, such early-stage design choices may lead to overall suboptimal processes and either increased resource cost or inferior product quality. Rigorous modelling and optimisation can help find efficient process designs and operating conditions while maintaining quality standards. However, such rigorous models require extensive modelling and experimental validation, creating a need for tools with moderate modelling requirements and focusing on data-value maximisation.
This project will utilise innovative machine learning methods and tools from process systems engineering to simultaneously optimise product quality and the manufacturing process from early development stages. This PhD project aims to develop computational tools that incorporate late-stage development into early-stage process and reaction optimisation. The project will combine digital twins based on established process designs and process engineering fundamentals with data-driven optimisation techniques, specifically Bayesian statistics and Bayesian optimisation.
The candidate will pursue research in machine learning, numerical optimisation, and process systems engineering, and collaborate with academics from the Department, the Sargent Centre, and industrial collaborators. Tasks include formulating optimisation problems, developing algorithms for optimisation with Bayesian models, and implementing solutions in relevant software. Further tasks include the formulation and development of modelling and system identification methodologies with a focus on data efficiency. The successful applicant will work on industrially defined case studies from the area of bioprocessing and specialised chemicals.
Person specification
The candidate should have a keen interest in computational work, including coding and software development, numerical optimisation, and machine learning. Prior experiences with numerical optimisation, machine learning, and chemical process design are highly beneficial. The ideal candidate pursues new insights, actively engages in scientific discussion, and is eager to collaborate with researchers in related fields. Further important qualities include a fundamental scientific rigour, creativity in thought and problem-solving, and independence in pursuit of opportunities and collaborations.
Eligibility
The candidate should have a background in engineering or in related STEM disciplines.
Applications from overseas applicants should include proof of the ability to cover the difference between home and overseas tuition.
The closing date for applications is May 31st, however the position may be filled sooner with a suitable candidate.
How to apply
Applications should be submitted through:
Funds are only available to cover UK-equivalent fees.
Overseas students may apply, provided they can independently cover the difference between UK and overseas tuition fees.
Please nominate Dr Eike Cramer as supervisor and include a statement of interest.
For informal enquiries please contact Dr Eike Cramer at: e.cramer@ucl.ac.uk
For further information on the MPhil/PhD course as well as the recruitment and selection process, please click on the link below:
Unlock this job opportunity
View more options below
View full job details
See the complete job description, requirements, and application process
