PhD position in Responsible Advice-Giving Systems

Have you always wondered how neural models process information Are you interested in high-impact research that helps ensure automatic systems provide unbiased transparent advice Do you enjoy turning open-ended questions into rigorous experiments and clear insights Are you interested in publishing impactful work at venues like SIGIR NeurIPS ACL or FAccT The IRLab is looking for an ambitious PhD candidate for responsible advice-giving systems that helps answer these questions.

Join one of the biggest labs on information retrieval in the world!

We are seeking a PhD candidate to work on responsible and interpretable advice-giving and information retrieval systems. You will carry out your research at the University of Amsterdam as part of the IRLab within the Informatics Institute.
How people access and engage with information has changed significantly over the past decades and especially in recent years. Automated systems are increasingly used to retrieve rank summarize and interpret information. While these developments create great opportunities for improving information access they also introduce substantial risks. Information is central to a democratic society therefore it is essential that such systems provide truthful unbiased and transparent this PhD position you will develop and evaluate approaches for responsible advice-giving and information retrieval systems (e.g. retrieval-augmented generation (RAG)) for instance by using interpretability techniques.

This is what you will do

As a PhD candidate you will conduct independent research on responsible and interpretable advice-giving systems and information retrieval. This research area includes several emerging subfields including (mechanistic) interpretability for RAG models and IR tasks the evaluation of explanations in IR biases in LLM-based IR models and the relationship between fairness and explainability in these settings. As such there is substantial room to contribute across a range of topics.
We are looking for an enthusiastic and creative individual who is interested in the following:

• Developing novel techniques to understand how information is processed within deep neural networks.
• Developing methods that achieve high accuracy while also being safe interpretable responsible and reliable.
• Developing evaluation frameworks to assess multiple dimensions of responsible advice-giving systems. Example dimensions include the faithfulness of explanations biases in generated answers and usefulness for different types of users.
• Connecting empirical findings about model behavior to theoretical frameworks of computation.
• Critically investigating the potential societal impact of proposed methods.
• Publishing and presenting findings at international AI conferences such as SIGIR ECIR NeurIPS ICML ICLR FAccT AAAI ACL EMNLP etc.

The exact research topics and work plan will be defined together with the selected candidate. We are open to a variety of directions and look forward to hearing your perspective on what responsible advice-giving should entail.

What we ask of you

Your experience and profile:

• MSc in artificial intelligence computer science engineering mathematics physics or a related discipline
• Demonstratable background in machine learning information retrieval or natural language processing
• Excellent software engineering skills in Python
• Fluent in English both written and spoken

This is what we offer you

A temporary contract for 38 hours per week for the duration of 4 years (the initial contract will be for a period of 18 months and after satisfactory evaluation it will be extended for a total duration of 4 years). The preferred starting date is as soon as possible. This should lead to a dissertation (PhD thesis). We will draft an educational plan that includes attendance of courses and (international) meetings. We also expect you to assist in teaching undergraduates and master students.

The gross monthly salary based on 38 hours per week and dependent on relevant experience ranges between 3059 to 3881 (scale P). This does not include 8% holiday allowance and 83% year-end allowance. The UFO profile PhD candidate is applicable.A favourable tax agreement the 30% ruling may apply to non-Dutch applicants. The Collective Labour Agreement of Universities of the Netherlands is applicable.

Curious about our extensive secondary benefits package You can read more about it here.

Where you will work

TheFaculty of Science has a student body of around 8000 as well as 1800 members of staff working in education research or support services. Researchers and students at the Faculty of Science are fascinated by every aspect of how the world works be it elementary particles the birth of the universe or the functioning of the brain.

The IRLab Amsterdam is part of the Informatics Institute of the University of Amsterdam. Our research focuses on information retrieval: technology to connect people to information. We work on search engines on recommender systems and on conversational assistants. There is a heavy emphasis on data-driven methods for understanding content for analyzing and predicting user behaviour and for make sense of context.

If you feel the profile fits you and you are interested in the job we look forward to receiving your application. You can apply online via the button below. We accept applications until and including 4 February 2026.

Applications should include the following information (all files besides your cv should be submitted in one single pdf file):

• a detailed CV including the months (not just years) when referring to your education and work experience;
• a letter of motivation including a description of your research interests and an explanation for why you are applying for this position (maximum 1 page); Since we are seeing a surge in AI-supported and AI-written letters which can be hard to distinguish we urge you not to use AI tools to compose this letter;
• a list of all Master-level modules you have taken with an official transcript of grades;
• a writing sample such as a Masters thesis a term paper or a publication (in case of joint authorship please clearly indicate your own contribution);
• the names and email addresses of two references who can provide letters of recommendation.

If you have any questions or do you require additional information Please contact:

• Dr. Maria Heuss Assistant Professor . Please quote PhD Position in the subject for requesting information