Book a call
Book a call

Postdoc Opportunity: Mechanistic Interpretability of LLM Reasoning at the University of Copenhagen

Postdoc position

9/26/2026

Want to dig into how LLMs actually acquire, integrate, and reason over evolving, pluralistic knowledge — using mechanistic interpretability methods? CopeNLU at the University of Copenhagen is recruiting a postdoc to do exactly that.

If you're drawn to the "why" and "how" behind model behavior rather than just the "what," this position sits at the heart of interpretability research, backed by an ERC Starting Grant and one of Europe's leading NLP environments.

About the Position

  • Role: Postdoctoral researcher

  • Host: CopeNLU group, Department of Computer Science, University of Copenhagen — affiliated with the Pioneer Centre for AI

  • Funding context: ERC Starting Grant ExplainYourself — Explainable and Robust Automatic Fact Checking, held by Isabelle Augenstein

  • Duration: 2 years, with possible extension contingent on funding

  • Start date: February 1, 2027 (or as close as possible)

  • Location: Central Copenhagen


What You'll Be Working On

Your core duty is to advance understanding of how LLMs acquire, integrate, and reason over evolving, pluralistic knowledge, using mechanistic interpretability methods. This could take the shape of new conceptual frameworks, new methods, or empirical studies — the position leaves real room to shape the research direction. You'll also take on a small amount of teaching or supervision alongside the research.

What They're Looking For

  • A PhD (or equivalent) in computer science or a related field

  • Good written and oral English skills

  • A track record of scientific publications and relevant work experience

  • Ideally, a background in natural language processing, machine learning, and/or explainable AI


About CopeNLU & the Pioneer Centre

CopeNLU is a collaborative research group led by Isabelle Augenstein and Pepa Atanasova, focused on fair and accountable NLP — spanning core methodology work on interpretability, explainability, and bias detection, as well as applications like fact checking and cross-cultural learning. The group is affiliated with the Pioneer Centre for AI, which pursues fundamental, interdisciplinary AI research across seven research themes (including Speech and Language) aimed at society's biggest challenges. The University of Copenhagen's NLP research environment is internationally leading — ranked second in Europe according to CSRankings.

How to Apply

👉 Apply here

Deadline: September 30, 2026, 23:59 CET

Meet the PI

Isabelle Augenstein, Dr. Scient., Ph.D.
Professor and Deputy Head of Department for Research
Department of Computer Science, University of Copenhagen
📧 augenstein@di.ku.dk
🔗 isabelleaugenstein.github.io

For more personalized tips or templates contact our team.

www.applywithmentors.com