Fully Funded Postdoctoral Researcher in Mechanistic Interpretability of AI Reasoning – University of Copenhagen, Denmark (CopeNLU / ExplainYourself Project)

Position Snapshot

• Institution: University of Copenhagen, Denmark

• Research Group: CopeNLU, led by Isabelle Augenstein and Pepa Atanasova

• Affiliations: ERC Starting Grant "Explainable and Robust Automatic Fact Checking" (ExplainYourself), and the Pioneer Centre for AI

• Level: Postdoctoral Researcher (full-time)

• Location: Department of Computer Science, Faculty of SCIENCE, University of Copenhagen — central Copenhagen

• Research areas:

  • Mechanistic interpretability of large language models (LLMs)

  • How LLMs acquire, integrate, and reason over evolving, pluralistic knowledge

  • Natural Language Processing, Machine Learning, Explainable AI

• Start date: 1 February 2027, or as close to this date as possible

• Duration: Two years, with possible extension contingent on funding availability

• Application deadline: 30 September 2026, 23:59 CET

• How to apply: Online application portal (link below)

About the Position

The CopeNLU group at the University of Copenhagen is recruiting a postdoctoral researcher to advance our understanding of the mechanisms underlying AI reasoning. The core focus of the role is to study how large language models acquire, integrate, and reason over knowledge that is evolving and pluralistic in nature, using mechanistic interpretability methods.

The work can take several forms — the development of novel conceptual frameworks, new interpretability methods, or empirical studies — and the successful candidate will have latitude in shaping their research direction within this scope. The role also carries a small teaching or supervision component.

The position sits within the context of the ERC Starting Grant held by Isabelle Augenstein on "Explainable and Robust Automatic Fact Checking" (ExplainYourself), and is further affiliated with the Pioneer Centre for AI.

Required Qualifications

Applicants should hold, or be close to completing, a PhD degree or equivalent in Computer Science or a related field, and have:

• Good written and oral English skills

• A track record of previous scientific publications relevant to the position

• Relevant prior work experience

An ideal candidate would have an educational background, prior research, or work experience in one or more of the following:

• Natural Language Processing

• Machine Learning

• Explainable AI

About the Group and Offering

The successful candidate will join the CopeNLU group at the University of Copenhagen. CopeNLU is a vibrant and collaborative research group led by Isabelle Augenstein and Pepa Atanasova, with a focus on fair and accountable NLP.

The group's research interests span:

• Core methodology research on interpretability, explainability, and bias detection

• Applications to tasks such as fact checking and cross-cultural learning

CopeNLU maintains a strong focus on both foundational and applied research, offering a platform for exploring cutting-edge topics in NLP while emphasising transparent and responsible AI development.

The group is affiliated with the Pioneer Centre for AI at the Department of Computer Science, Faculty of SCIENCE, University of Copenhagen, located in central Copenhagen. The Pioneer Centre focuses on fundamental AI research and, within an interdisciplinary framework, develops platforms, methods, and practices addressing society's greatest challenges. It consists of seven AI research themes, one of which is Speech and Language.

Why the University of Copenhagen?

The Natural Language Processing research environment at the University of Copenhagen is internationally leading — evidenced, for example, by its ranking as second in Europe according to CSRankings. Joining CopeNLU means becoming part of an active, collaborative, and multi-cultural research group at the heart of one of Europe's strongest NLP hubs.

Why This Opportunity Stands Out

This postdoctoral position offers:

• A rare opportunity to work at the forefront of mechanistic interpretability, one of the fastest-growing areas in AI safety and reasoning research

• Affiliation with a top-ranked European NLP research environment

• Backing from a competitive ERC Starting Grant and the Pioneer Centre for AI

• Supervision and mentorship from Isabelle Augenstein and Pepa Atanasova, established leaders in explainable and accountable NLP

• The flexibility to shape research direction — through new frameworks, methods, or empirical studies

• A collaborative, international group culture in a high quality-of-life European capital

How to Apply

Apply online by 30 September 2026, 23:59 CET to be considered:

Application link: https://candidate.hr-manager.net/ApplicationInit.aspx/?cid=3010&departmentId=19976&ProjectId=167176&MediaId=4917&SkipAdvertisement=false

For candidates passionate about interpretability, AI reasoning, and explainable AI, this is an exceptional opportunity to pursue high-impact postdoctoral research within one of Europe's leading NLP groups.

For more personalized tips or templates contact our team.

www.applywithmentors.com