PhD in Nuclear Fuel Performance Modelling with Machine Learning at Uppsala University (with Westinghouse and Vattenfall)
Job Description
Uppsala University’s Division of Applied Nuclear Physics is recruiting a PhD student in nuclear fuel performance modelling using machine learning, in close collaboration with Westinghouse and Vattenfall within the ANItA competence centre. Building on earlier work on calibrating fuel performance codes, the project develops statistical calibration, uncertainty quantification and temporal machine-learning surrogate models for fast, reliable predictions of fuel behaviour, demonstrated on problems such as cladding hoop stress and the risk of pellet-cladding interaction damage.
At a glance
- Position: Doctoral student (1 post), full time
- Where: Department of Physics and Astronomy, Uppsala, with industrial co-supervision
- Partners: Westinghouse and Vattenfall
- Apply by: 30 September 2026
- Apply: 30 September 2026
About the fuel performance PhD
- Develop calibration methods using time-dependent and axially resolved measurement data
- Propagate uncertainties between coupled, calibrated sub-models without double counting
- Build temporal sequence-to-sequence ML models of fuel behaviour, covering different fuel types, enrichments and gadolinia content
- Test how models generalise beyond their training data and demonstrate them in industrial applications
- Implement documented tools in Python, publish and present; teaching up to 20% of working time
About ANItA
ANItA (Academic-industrial Nuclear technology Initiative to Achieve a sustainable energy future) is a Swedish competence centre that brings academia and industry together to strengthen nuclear engineering expertise, including work on small modular reactors.
PhD applicants: browse our Find a supervisor directory to see who works in your area.
What Uppsala University is looking for
- A master’s degree in engineering physics, nuclear engineering, applied physics, computational science, applied mathematics, statistics, machine learning or a relevant area, or equivalent credits
- Good knowledge of physics, numerical methods, statistics and/or machine learning
- Good programming skills, for example in Python, Julia or C++
- Structured independent work, good collaboration and good English
Nice to have
- Nuclear fuel or fuel-performance modelling, reactor physics or nuclear engineering
- Numerical modelling of heat transfer or material behaviour
Pay and location
Swedish doctoral students are salaried employees on a fixed-term contract; Uppsala’s advert gives no figure. The post is full time in Uppsala.
How to apply
Apply through the official Uppsala University page. The closing date is 30 September 2026.
See all our PhD positions, or browse more research jobs on ResearchJobs.in.
Hiring institution: Uppsala University
Official advertisement: uu.varbi.com
How to prepare for this application
- UQ experience: Bayesian calibration or uncertainty propagation work is directly relevant.
- Sequence models: describe any LSTM, transformer or other time-series surrogate you have built.
- Industry fit: the project is co-supervised with industry, so mention any industrial collaboration.
- Physics grounding: revise heat transfer in fuel rods and basic fuel behaviour.
- Deadline: applications close on 30 September 2026.
About Uppsala University
Uppsala University, founded in 1477, is Sweden's oldest university and a broad research university. Its science and technology departments are largely based at the Ångström Laboratory.
