Postdoctoral Researcher in Simulation-Based Inference for Particle Physics

Uppsala Universitet · Full-time

box 256, Uppsala, Sweden

Do you want to work with machine learning and simulation-based inference in the search for dark matter (or other "invisible" signals of new physics) at the Large Hadron Collider, in an international environment with competent and friendly colleagues? We invite you to apply for a postdoctoral position at Uppsala University. This is a shortened version of the job posting. The complete posting is available on Uppsala University's website, uu.se/jobb. The Department of Information Technology is Uppsala University's third largest department with approximately 350 employees. The position is located at the Division for Computational Science (TDB), one of the world's largest research environments in computational science with extensive activities in machine learning, optimization, and high-performance computing, and an important part of eSSENCE and SciLifeLab. The hired researcher will join the Scientific Machine Learning research group at TDB and SciLifeLab (University Lecturer Prashant Singh), which develops methods and software for simulation-based inference, generative models, and robust machine learning, in close collaboration with the Theoretical Particle Physics group at the Department of Physics and Astronomy (Professor Stefano Moretti), which conducts research on beyond-standard-model phenomenology and dark matter and is a member of the CMS experiment at CERN. The project establishes a new cross-faculty collaboration where new simulation-based inference methodology is developed and applied directly to realistic analyses of collider data. The postdoctoral researcher will be jointly supervised by both groups and will receive support for conference travel as well as access to national HPC resources (NAISS) and local GPU infrastructure. The position is part of the eSSENCE graduate school in data-intensive science, an arena where experts in computational science, data science, and data technology work closely with researchers in data-driven sciences, industry, and society. eSSENCE is a strategic research collaboration in e-science between Uppsala University, Lund University, and Umeå University. Project Description The search for dark matter at the LHC involves comparing high-dimensional collision data with detailed simulations whose likelihood cannot be calculated, only sampled. Simulation-based inference (SBI) addresses this by training neural networks, such as generative models based on flow matching, on simulated events. The project aims to develop efficient, robust, and calibrated SBI methods that account for event selection and systematic uncertainties, and to demonstrate them in realistic large-scale searches. The project is primarily based on simulated data, but there is also an opportunity to work with open data from ATLAS and/or CMS. The methods are general and applicable far beyond particle physics. Duties Research within the project, including method development, implementation, large-scale computational experiments, and publication, as well as presentations at international conferences, contributions to the group's open-source software, participation in eSSENCE graduate school activities, and involvement in student mentoring. A limited amount of teaching may be included (maximum 20%). Qualification Requirements A PhD in machine learning, computational science, statistics, physics, or a related field, or a foreign degree assessed as equivalent to a PhD in these areas. The degree must be completed by the time the employment decision is made. Preferably, the degree should have been obtained no more than three years ago. When calculating the three-year period, the starting point is the application deadline. If there are special circumstances, such a degree may have been obtained earlier. Special circumstances include leave due to illness, parental leave, positions of trust within trade union organizations, etc. Documented experience in machine learning, particularly deep generative models and/or probabilistic modeling, as well as very strong programming skills in Python and a modern deep learning framework (e.g., PyTorch or JAX) are required. Strong knowledge of English in speaking and writing is required. The candidate must clearly demonstrate a high degree of self-motivation in the application. Great importance is placed on personal qualities such as creativity, attention to detail, a structured work approach, and the ability to work both independently and in an interdisciplinary team. Desirable/Meriting Experience Experience with simulation-based inference, normalizing flows, flow matching, or diffusion models; with particle physics (e.g., MadGraph, Pythia, Delphes, or LHC data analysis); with large-scale training on GPU/HPC systems, active learning, and open-source software development is meriting, as are publications at leading machine learning conferences or physics journals. Teaching experience (e.g., teaching, mentoring, supervision, or other pedagogical activities) is meriting but not required; particular emphasis is placed on activities that support student learning in data science, information technology, or related fields. Application The application should include: CV; Copy of relevant transcripts (in Swedish or English); List of publications; up to five selected publications in electronic format; A research description of previous and current research (max 1 page) and a proposal for future activities (max 1 page); Contact information for two references. In this recruitment, we have replaced the personal letter with questions that you answer in connection with your application. The answers are used as part of the selection process. About the Position The position is time-limited for two years according to central collective agreement. Full-time. Start date November 1, 2026, or by agreement. Location: Uppsala. Information about the position is provided by: University Lecturer Prashant Singh, [email protected]; Professor Stefano Moretti, [email protected]; Head of Division Elisabeth Larsson, [email protected]. Welcome to submit your application by Thursday, October 15, 2026, UFV-PA 2026/2734.