Overview
About the position
Integreat – the Norwegian Centre for Knowledge-driven Machine Learning at the University of Oslo – invites applications for a postdoctoral fellowship in preference learning for LLMs. We seek a motivated researcher who values collaboration, inclusivity, and impact, and who will contribute to a supportive, interdisciplinary research environment with a strong focus on mentoring and career development.
Starting date: upon individual appointment and no later than 1 October 2026.
The appointment is a fulltime position at the Department of Informatics and is for a period of three years. Depending on the candidate and the teaching needs of the department, the fellowship period can be extended for either compulsory work consisting of e.g., teaching and supervision duties and research assistance up to four years.
No one can be appointed for more than one Postdoctoral Research Fellowship at the University of Oslo.
Place of work is Integreat – Norwegian Centre for Knowledge-driven Machine Learning at Blindern, University of Oslo.
About the project
The intended focus of the position is to advance the research on preference learning for LLMs, including the use of synthetic data, and in particular for data-constrained settings. We welcome applicants with a strong background in NLP and practical experience with LLM development; experience in statistical modelling is an advantage. The project involves close interdisciplinary collaboration between statisticians and NLP researchers at Integreat.
The position is also affiliated with the Language Technology Group (LTG) at the UiO Department of Informatics (IFI). LTG is an international and diverse group, with research targeting a broad range of areas within NLP, including training and benchmarking of large language models (LLMs). The research profile of the group is heavily machine-learning oriented and the group has access to excellent HPC infrastructure. For more information about LTG, please see: http://www.mn.uio.no/ifi/english/research/groups/ltg/
The successful applicant will benefit from close collaboration across disciplines and access to diverse application areas through the joint environment of Integreat and LTG.
The main purpose of a postdoctoral fellowship is to provide the candidates with enhanced skills to pursue a scientific top position within or beyond academia. To promote a strategic career path, all postdoctoral research fellows are required to submit a professional development plan no later than one month after commencement of the postdoctoral period. Professional development plan for postdoctoral research fellows – The Faculty of Mathematics and Natural Sciences.
Integreat provides a researcher training programme, INTREF — the Integreat Young Researchers’ Forum — a fellow driven initiative offering scientific training, transferable skills workshops, mentorship, research visits, and career development support.
Company:
Univresity of Oslo
Qualifications:
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.
Qualification requirements:
The candidate must have a PhD degree (or other corresponding education equivalent to a Norwegian doctoral degree) in Natural Language Processing, or in Computer Science with a clearly NLP-based dissertation.
The doctoral dissertation must have been submitted for evaluation by the closing date. Only applicants with an approved doctoral thesis and public defence are eligible for appointment.
Fluent oral and written communication skills in English.
Demonstrated research excellence in NLP, evidenced by publications in top‑tier peer‑reviewed NLP conferences or journals.
The candidate must demonstrate broad knowledge of core NLP tasks.
The candidate must have comprehensive knowledge of contemporary neural machine learning techniques and architectures in NLP, both in terms of theoretical understanding and practical experience, including fine-tuning of Large Language Models (LLMs).
Strong programming skills and implementation experience
Desired qualifications:
Background in statistics or experience with large-scale ML experimentation (HPC) is beneficial.
Experience mentoring students, collaborative research, and reproducible ML practices are valued.
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.
Educational level:
Ph. D.
