PhD Research Fellow in Trustworthy Machine Learning
Deadline: 24.03.2026
Publisert
The University of Oslo is Norway’s oldest and highest rated institution of research and education with 26 500 students and 7 200 employees. Its broad range of academic disciplines and internationally esteemed research communities make UiO an important contributor to society.
The Department of Informatics (IFI) is one of nine departments belonging to the Faculty of Mathematics and Natural Sciences. IFI is Norway’s largest university department for general education and research in Computer Science and related topics.
The Department has more than 1800 students on bachelor level, 600 master students, and over 240 PhDs and postdocs. The overall staff of the Department is close to 370 employees, about 280 of these in full time positions. The full time tenured academic staff is 75, mostly Full/Associate Professors.
About the position
We invite applications for position as PhD Research Fellow in Machine Learning available at Department of Informatics, Faculty of Mathematics and Natural Sciences, University of Oslo.
Starting date no later than 01.10.2026.
The fellowship period is three years.
A fourth year may be considered and it will involve 25 % of other career-promoting work. Other career-promoting work may consist of teaching, supervision, and/or research assistance. This is dependent upon the qualification of the applicant and the current needs of the department.
No one can be appointed for more than one PhD Research Fellowship period at the University of Oslo.
Place of work is Department of Informatics at Blindern, Oslo.
Job description
Unsupervised machine learning (ML) methods are widely used to explore structure in complex and high-dimensional data, particularly in the life sciences, where clustering analyses often form the basis for biological interpretation and hypothesis generation. In practice, the conclusions drawn from such analyses rest on a set of often implicit assumptions about what constitutes a meaningful or reliable result, for example, that stable solutions under realistic data perturbation are good indicators of the underlying structure, or that internal validation criteria capture the relevant aspects of the data and their representation. Many such assumptions are widely relied upon, yet rarely examined explicitly. In high-dimensional settings, these assumptions are especially difficult to justify, as sparsity and the curse of dimensionality make the identification and interpretation of the latent structure more challenging. This project addresses these challenges within the framework of trustworthy machine learning to clarify when unsupervised analyses, particularly clustering, can be meaningfully trusted to reflect properties of the underlying data-generating process.The central research challenge is to understand how clustering approaches and validation procedures behave as the data-generating process departs from idealized conditions and as dimensionality, heterogeneity, and structural complexity increase. The project will develop a simulation-based benchmarking framework that enables systematic exploration across controlled data-generating processes, explicitly designed to probe the assumptions underlying common unsupervised workflows. This exploration will include synthetic settings with known ground truth, as well as realistic and challenging use cases, such as adaptive immune receptor repertoires and gene expression data, which combine extremely high dimensionality, sparsity, and a strong need for biological interpretability. In such settings, current practice in applying clustering often falls short: multiple biologically plausible definitions of “true” clusters coexist, analyses typically rely on a single dataset and potentially misleading validation metrics, and robustness is seldom evaluated systematically (e.g., via stability assessments). By varying key properties of the data-generating process, the project will seek to identify not only characteristic failure modes of existing approaches, but also methodological patterns associated with more reliable structure discovery.
The project adopts a unified and assumption-aware perspective on evaluation, emphasizing robustness analysis, sensitivity to modeling choices, and complementary empirical tests as essential components of trustworthy unsupervised learning in high-dimensional settings. Causality will be used as one analytical lens to assess when observed structure plausibly reflects underlying mechanisms rather than artifacts introduced by confounders or preprocessing choices. The resulting insights will inform practical guidance for model selection, validation, and workflow design, while more broadly contributing to a deeper understanding of what it means to trust unsupervised learning as an exploratory tool in scientific machine learning applications.
The PhD position will be embedded in the SCML research group and contribute to its ongoing interdisciplinary work at the intersection of machine learning and life sciences. Dr. Milena Pavlović will serve as a primary supervisor for the project, with professors Anne-Marie George, Pooya Zakeri, and Torbjørn Rognes serving as co-supervisors. The candidate will collaborate with other PhD students and researchers in the group, particularly within existing life science projects. The position also offers opportunities for engagement with TRUST - The Norwegian Centre for Trustworthy AI, especially within the veridical AI research theme, fostering connections to broader interdisciplinary efforts in trustworthy and reliable AI and machine learning.
What skills are important in this role?
The Faculty of Mathematics and Natural Sciences has a strategic ambition to be among Europe’s leading communities for research, education and innovation. Candidates for these fellowships will be selected in accordance with this, and expected to be in the upper segment of their class with respect to academic credentials.
Required qualifications:
Master’s degree or equivalent in computer science, statistics, data science or related field
Foreign completed degree (M.Sc.-level) corresponding to a minimum of four years in the Norwegian educational system
Documented experience in machine learning, in the form of completed machine learning courses at bachelor’s or master’s level, or bachelor’s or master’s level projects with focus on machine learning
Fluent oral and written communication skills in English
Candidates without a master’s degree have until June 30, 2026 to complete the final exam.
Desired qualifications:
Experience with data simulation, clustering algorithms, benchmarking, model selection and evaluation workflows is an advantage
Language requirement:
Good oral and written communication skills in English
The average grade point for courses included in the Bachelor’s degree must be C or better in the Norwegian educational system
The average grade point for courses included in the Master’s degree must be B or better in the Norwegian educational system
The Master’s thesis must have the grade B or better in the Norwegian educational system
The purpose of the fellowship is research training leading to the successful completion of a PhD degree. For more information see:http://www.mn.uio.no/english/research/phd/
All candidates and projects will have to undergo a check versus national export, sanctions and security regulations. Candidates may be excluded based on these checks. Primary checkpoints are the Export Control regulation, the Sanctions regulation, and the national security regulation.
What are we looking for in you?
Personal skills:
Curious, open-minded and motivated to learn
Strong interest in rigorous academic research
Comfortable working both independently and collaboratively
Proactive in taking ownership of research questions
Collaborative mindset with a strong sense of responsibility for high-quality research
Willing to actively contribute to an inclusive, respectful and collegial research culture
Prefer being present at work and actively contributing to the professional and social environment you are a part of
Employment in the position is based on a comprehensive assessment of all qualification requirements applicable to the position, including personal qualifications.
Membership in the Statens Pensjonskasse, which is one of Norway's best pension schemes with beneficial mortgages and good insurance schemes
Oslo’s family-friendly surroundings with their rich opportunities for culture and outdoor activities
Salary in position as PhD Research Fellow, position code 1017 in salary range NOK from 550 800 - 595 000, depending on competence and experience. From the salary, 2 percent is deducted in statutory contributions to the State Pension Fund
We need different perspectives in our work
UiO is an open and internationally oriented comprehensive university that strives to be an inclusive and diverse workplace and academic environment. You can read more about UiO’s work on equality, inclusion, and diversity at uio.no.
We fulfill our mission most effectively when we draw upon our variety of experiences, backgrounds, and perspectives. We are looking for great colleagues, could you be the next one?
We will do our best to accommodate your needs. Relevant adjustments may include modifications to working hours, task adaptations, digital, technical, or physical adjustments, or other practical measures.
If you have an immigrant background, a disability, or CV gaps (Norwegian), we encourage you to indicate this in the job application portal. We always invite at least one qualified candidate from each group for an interview. In this context, disability is defined as an applicant who identifies as having a disability that requires workplace or employment-related accommodations. For more details about the requirements, please refer to the Employer portal (Norwegian).
The selections made in the job application portal are used for anonymized statistics that all state employers include in their annual reports. More information about gender equality initiatives at UiO can be found here. We hope you will apply for the position with us.
How to apply
The application must include:
Cover letter - statement of motivation and research interests
CV (summarizing education, positions and academic work - scientific publications)
Transcripts of records, copies of the original Bachelor’s and Master’s degree diploma (see below)
Documentation of English proficiency if applicable
List of publications and academic work that the applicant wishes to be considered by the evaluation committee
Names and contact details of 2-3 references (name, relation to candidate, e-mail and telephone number)
Application with attachments must be submitted via our recruitment system Jobbnorge, click "Apply for this job". Foreign applicants should attach an official explanation of their University's grading system.
When applying for the position, we ask you to retrieve your education results from Vitnemålsportalen.no. If your education results are not available through Vitnemålsportalen, we ask you to upload copies of your transcripts or grades. Please note that all documentation must be in English or a Scandinavian language.
General information
The best qualified candidates will invited for interviews.Applicant lists can be published in accordance with Norwegian Freedom of Information Act § 25. When you apply for a position with us, your name will appear on the public applicant list. It is possible to request to be excluded from this list. You must justify why you want an exemption from publication and we will then decide whether we can grant your request. If we can't, you will hear from us.
