Home PhD PhD Fellowship in Mechanistic Interpretability for LLM Security, University of Copenhagen, Denmark

PhD Fellowship in Mechanistic Interpretability for LLM Security, University of Copenhagen, Denmark

The University of Copenhagen has four campus areas. As distances in Copenhagen are relatively small, it is easy to get from one campus to the other either by bicycle or public transportation. The campus areas are integrated into the city of Copenhagen and students use the facilities available in the city, adding a lively buzz to the streets and cafés of Copenhagen.

Summary

The University of Copenhagen is inviting applications for a PhD fellowship focused on developing a mechanistic framework to enhance the security of large language models (LLMs). This research is part of a project funded by the Independent Research Foundation Denmark and aims to mitigate the susceptibility of LLMs to false information.

PhD Fellowship in Mechanistic Interpretability for LLM Security, University of Copenhagen, Denmark

Designation

PhD Fellowship

Table

ElementDetails
Research AreaMechanistic Interpretability, LLM Security, Natural Language Processing, Explainable AI
LocationUniversity of Copenhagen, Department of Computer Science, Copenhagen, Denmark
Eligibility/Qualification– MSc degree in Computer Science or a related field
– Good written and oral English skills
– Relevant experience in ML or NLP is preferred
Job Description– Conduct research on mechanistic interpretability methods
– Collaborate with the project team
– Publish scientific papers
– Attend courses
How to ApplySubmit an application including:
– Cover letter
– Research statement
– CV
– Copies of relevant diplomas
– Publication list
– References
Last Date for Apply31 May 2026, 23:59 GMT +1

Research Area

The focus will be on mechanistic interpretability methods to reduce the impact of false information and enhance LLM security at various stages of the model lifecycle.

Location

University of Copenhagen, Department of Computer Science, Copenhagen, Denmark.

Eligibility/Qualification

  • A Master’s degree or equivalent in Computer Science or a related field.
  • Strong written and oral communication skills in English.
  • Previous research or work experience in Machine Learning (ML) or Natural Language Processing (NLP) is desirable.

Job Description

The PhD candidate will:

  • Develop a research project aligned with the overarching goals of the project.
  • Collaborate with both internal and external research partners.
  • Author and disseminate research papers in high-impact venues.
  • Engage in academic courses for skill development.
  • Write and defend a PhD thesis based on their research findings.

How to Apply

Interested candidates should submit their applications electronically, including:

  1. Cover Letter detailing motivation and background.
  2. Research Statement outlining desired focus within the PhD studies.
  3. Curriculum Vitae with educational and relevant experience.
  4. Original academic diplomas and transcripts.
  5. Publication list (if applicable).
  6. Contact information for three references.

Last Date for Apply

Applications must be submitted by 31 May 2026, 23:59 GMT +1. Applications received after this deadline or that do not meet the requirements will not be considered.

Link

LEAVE A REPLY

Please enter your comment!
Please enter your name here