"Three PhD Student Positions in Generative Information Retrieval"

Are you interested in cutting-edge research at the intersection of large language models, deep learning, and information retrieval? The Information Retrieval Lab (IRLab) at the University of Amsterdam is looking for PhD candidates to join our research team and contribute to the development of next-generation retrieval systems based on generative models.

We are seeking highly motivated PhD candidates to work on topics in Generative Information Retrieval (GenIR), a new and rapidly evolving retrieval paradigm where generative models are used to directly generate document identifiers given a user query. This paradigm departs from traditional multi-stage retrieval pipelines and instead integrates the indexing and retrieval process into a single, end-to-end generative model.

As such, GenIR models are able to more deeply interact with the underlying corpus, enabling enhanced reasoning, adaptability, and performance in real-world scenarios. These positions are embedded within the Information Retrieval Lab (IRLab), under the supervision of Maarten de Rijke. They are part of a broader research effort to establish a principled foundation for GenIR and are funded by the European Research Council under grant agreement no. 101201510 (UNITE).

What are you going to do? Generative information retrieval (GenIR) is an emerging retrieval paradigm where generative models directly produce document identifiers in response to a query, enabling a tight integration of retrieval and generation. While there are promising applications in both academic and industrial settings, several important open challenges remain. These include out-of-distribution performance, low-resource settings, reliability, dynamic settings, and transparency.

Tasks and responsibilities
You will:

• Conduct research within the scope of the PhD project;
• Complete and defend a PhD thesis within the official appointment duration (four years);
• Publish your research in international conferences and journals;
• Present your work to both scientific and non-scientific audiences;
• Be an active member of the research group and participate in internal and external research activities;
• Contribute to teaching activities, such as mentoring students and giving guest lectures.

What we ask of you
We are looking for enthusiastic and curious candidates who meet the following profile:

• Educational background: You hold (or are close to obtaining) a Master’s degree in Computer Science, Artificial Intelligence, Data Science, or a closely related discipline;
• Interests: You should have a strong interest in deep learning and information retrieval;
• Programming skills: You have strong programming skills and experience with deep learning frameworks (e.g., PyTorch, TensorFlow);
• Teamwork and independence: You are motivated to contribute to open science and reproducible research, and you are able to work both independently and as part of a team;
• Communication skills: You have strong written and verbal communication skills in English. Prior experience with large language models, generative methods, and/or retrieval tasks is advantageous but not required.

What we offer
We offer 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 in early to mid-2026. This should lead to a dissertation (PhD thesis).

The gross monthly salary, based on 38 hours per week and dependent on relevant experience, ranges between €3,059 to €3,881 (scale P). This does not include 8% holiday allowance and 8.3% 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.