Chalmers University of Technology
Just Landed
New Today
Doctoral student in Explainable Machine Learning for Nuclear Safeguards Chalmers University of Technology in Sweden
Degree Level
PhD
Field of study
Computer Science
Funding
The doctoral student position is fully funded from the start. It is a fixed-term appointment of four years, extendable up to five years if teaching up to 20% of working hours is included. Starting salary is 35,725 SEK per month from May 1, 2026.
Deadline
Nov 23, 2026
Country
Sweden
University
Chalmers University of Technology
How do I apply for this?
Sign in for free to reveal details, requirements, and source links.
Apply for this position
Keywords
Suggested positions
About this position
Chalmers University of Technology is advertising a doctoral student position in Explainable Machine Learning for Nuclear Safeguards within the Reactor Physics, Modelling and Safety group at the Department of Physics and Astronomy in Gothenburg, Sweden.
The project sits at the intersection of computer science, physics, mathematics, machine learning, deep learning, explainable AI (XAI), reactor physics, and nuclear safeguards. The research focuses on developing an XAI framework for spent nuclear fuel (SNF) safeguards inspection, making ANN-based predictions more transparent and useful for critical verification decisions.
You will investigate how to integrate multiple XAI methods, study semantic layers for aggregating predictions into actionable explanations, and use explainability insights to improve ANN architectures, training strategies, and robustness. The role includes doctoral research, publication of results in journals and conferences, and advanced coursework in the Graduate School of Nuclear Engineering.
The position is fully funded from the start. It is a fixed-term appointment for four years, with the possibility to extend to five years if teaching or other duties up to 20% are included. The starting salary is 35,725 SEK per month (from May 1, 2026).
Applicants must hold a relevant Master’s degree in Physics, Mathematics, Computer Science, or equivalent; for applicants educated outside Sweden, a 4-year Bachelor’s degree is accepted. Strong English communication skills are required, along with experience in at least one of machine learning, deep learning, explainable AI, reactor physics, or nuclear safeguards, plus solid programming skills such as Python.
The application deadline is November 23, 2026. Apply online via the job portal and submit the required PDF documents: CV, personal letter, brief introduction and motivation, and bachelor’s and, if available, master’s thesis with transcripts. Applications sent by email or incomplete applications will not be considered.
Funding details
The doctoral student position is fully funded from the start. It is a fixed-term appointment of four years, extendable up to five years if teaching up to 20% of working hours is included. Starting salary is 35,725 SEK per month from May 1, 2026.
What's required
Applicants must have a Master's degree (120 credits) or a 60-credit Master’s degree in Physics, Mathematics, Computer Science, or equivalent; for students educated outside Sweden, a 4-year Bachelor’s degree is accepted. Strong written and verbal English skills are required. Candidates should have background or experience in at least one of Machine Learning, Deep Learning, Explainable AI, Reactor Physics, or Nuclear Safeguards, plus solid computational methods and strong programming skills such as Python. Collaborative ability, responsibility, and strong analytical skills are expected.
How to apply
Prepare the application in English and upload the required PDF files through the application form on the job page. Include a CV, personal letter, brief introduction and motivation, and bachelor’s and, if available, master’s thesis together with transcripts. Do not send applications by email; incomplete applications will not be considered.
More information can be found here
Ask ApplyKite AI
How do I apply for this?
Sign in for free to reveal details, requirements, and source links.