PhD Candidate in Core Optimization with Machine Learning

Popis:

Do you want to work with machine learning, optimization, and reactor physics, supported by competent and friendly colleagues in an international environment? Do you want to contribute to the development of advanced computational methods for future nuclear power systems? Do you want an employer that invests in sustainable employee relations and offers secure, favorable working conditions? We welcome your application for a PhD position at Uppsala University. As a PhD candidate, you will be part of a research group working on reactor physics, fuel cycle analysis, and computational methods for core and fuel optimization. The group combines physics-based computational models with modern optimization and data analysis methods. The work environment is international and multidisciplinary, with close links between fundamental method development and technically relevant applications. The project is a continuation of an ongoing PhD project on core and fuel optimization for small modular reactors (SMR) within the competence center ANItA (Academic-industrial Nuclear technology Initiative to Achieve a sustainable energy future). The competence center brings together academia and industry to strengthen Swedish nuclear technology expertise and contribute to a sustainable energy transition. The previous PhD project has developed methods for optimizing equilibrium cycles, where the goal is to find recurring fuel management strategies that provide good fuel economy while meeting reactor physics safety margins. Special focus has been on combining advanced optimization algorithms with machine learning-based surrogate models, including graph-based representations of core loading patterns. You will further develop this research direction. The project may include cycle-to-cycle optimization, development of new machine learning models, improved optimization strategies, uncertainty quantification, more efficient handling of physical constraints, and expanded analysis of fuel design, loading patterns, and safety-related quantities. The goal is to develop methods that enable faster and more reliable exploration of large design spaces in core and fuel optimization. Duties The duties consist mainly of doctoral studies, where you conduct research within the project and complete courses as part of your doctoral education. The work involves developing, implementing, and evaluating computational methods for core and fuel optimization using machine learning and optimization algorithms. Your duties include: - Develop and apply machine learning-based surrogate models for reactor physics calculations, - Develop and evaluate optimization methods for fuel loading patterns and fuel composition, - Analyze safety-related parameters such as reactivity, power distributions, fuel utilization, and margins to technical limits, - Work with large datasets from reactor physics simulations, - Implement and document computational tools, for example in Python, - Compile and publish research results in scientific articles, - Present results at national and international conferences, - Participate in research group seminars, project meetings, and other scientific activities. Teaching and other institutional service may be included with a maximum of 20 percent of full-time work. Qualifications To be eligible for doctoral studies, you must have: - Completed an advanced degree in engineering physics, nuclear engineering, energy engineering, machine learning, computer science, applied mathematics, or another field relevant to the project, or - Completed at least 240 credits, of which at least 60 credits at advanced level including an independent thesis of at least 15 credits, or - Acquired equivalent knowledge in another way. For the position, the following is also required: - Strong knowledge in physics, numerical methods, and/or machine learning, - Good programming skills, for example in Python, Julia, C++, or equivalent, - Ability to work independently and in a structured manner, - Good ability to collaborate, - Good ability to express yourself orally and in writing in English. Great weight will be placed on personal qualities such as analytical ability, initiative, accuracy, and motivation to conduct research within a multidisciplinary field. Desirable/Merits It is meritorious to have experience in one or more of the following areas: - Reactor physics, nuclear engineering, or neutron transport, - Core optimization, fuel cycle analysis, or fuel management, - Machine learning, especially neural networks, graph neural networks, or surrogate modeling, - Optimization algorithms, such as evolutionary algorithms, stochastic optimization, or multi-objective optimization, - Uncertainty quantification or statistical modeling, - Work with scientific computing software and high-performance computing, - Experience with version control and reproducible computing workflows. Regulations for PhD candidates are found in the Higher Education Ordinance Chapter 5 §§ 1-7 and in the university's rules and guidelines. About the Application Please attach transcripts, a copy of your thesis, and any other documents you wish to submit. About the Position The position is time-limited, according to the Higher Education Ordinance Chapter 5 § 7. Full-time. Start date: January 1, 2027, or by agreement. Location: Uppsala. Information about the position is provided by: Andreas Solders, 018-471 26 31, [email protected] In this recruitment, we have replaced the personal letter with questions that you answer as part of your application. Your answers will be used as part of the selection process. Welcome to submit your application no later than September 30, 2026, UFV-PA 2026/2129 Note that this is an abbreviated version of the announcement. To see the full announcement, please click on "Apply here" or visit Uppsala University's job announcement website.

Přehled

Typ

job

Stav

active

Viditelnost

public

Město

Uppsala

Adresa

Box 256

GPS

59.8520701, 17.7188369kopírovatotevřít v ▾

Email

[email protected]

Telefon

018-471 26 31

Zobrazení

5

Publikováno

17. 6. 2026

Upraveno

21. 6. 2026

Parametry