Postdoctoral Researcher in Learning from Interaction Signals for Search and Recommendation

We are looking for a motivated and creative Postdoctoral Researcher to join the Information Retrieval Lab at the University of Amsterdam in a position that is part of the Mercury Machine Learning Lab a collaboration between the University of Amsterdam and Booking AI Research. This position is ideal for candidates eager to publish high-impact research in top-tier conferences and journals while being inspired by new questions that challenging real-world applications bring up. The Mercury Machine Learning lab brings together PhD students PostDocs Professors and PIs from different disciplines Information Retrieval and Natural Language Processing which makes this position specifically interesting for researchers wanting to use multiple of these disciplines.

The successful candidate will investigate how implicit and explicit user feedback can be used to correct align fine-tune and evaluate models and LLMs in retrieval and recommendation settings building on foundational work in learning to rank and on emerging methods for preference learning and reinforcement learning from human feedback. Key open questions include how to use multi-turn conversational signals how to correct for position and presentation biases when interaction data is generated by LLM-driven interfaces and how to design evaluation frameworks that are robust to feedback sparsity and noise. The specific focus area will be driven by the background of the researcher.

Candidates should have a strong background in information retrieval machine learning or natural language processing with interest in bridging the gap between interaction-based learning and modern generative systems.

• help develop study and apply machine learning techniques for learning from user interaction signals in search and recommendation systems in collaboration with data scientists from and under supervision of dr. Zoeter and prof. Rijke;
• investigate methods for leveraging implicit and explicit feedback to improve retrieval recommendation and LLM-based systems;
• study challenges such as multi-turn conversational signals position and presentation bias correction and robust evaluation under sparse and noisy feedback;
• publish research results in top-tier international journals and present at leading conferences;
• assist with the research and the supervision of PhD students involved in the MMLL initiative;
• collaborate with other MMLL and AI researchers across information retrieval machine learning and NLP;
• assist in relevant teaching and knowledge dissemination activities

• A PhD degree (or equivalent qualification) in information retrieval machine learning natural language processing or a closely related field;
• an exceptional scientific track record documented by publications at first-tier journals and conferences;
• a strong research background in topics related to information retrieval recommendation systems learning to rank preference learning reinforcement learning from human feedback or LLMs;
• interest in bridging interaction-based learning approaches with modern generative AI systems;
• excellent mathematical and analytical skills;
• excellent programming skills;
• excellent communication presentation and writing skills;
• an excellent command of English;
• commitment perseverance and a cooperative attitude

The postdoc researcher will spend two days a week in the office of in Amsterdam to do research and actively participate in related streams of experimentation to test their hypotheses.

We offer a temporary employment contract for 38 hours per week for a period of maximum 12 months. The preferred starting date is as soon as possible and preferably in August 2026.

The gross monthly salary based on 38 hours per week and dependent on relevant experience ranges between 3546 to 5538 (scale 10). This does not include 8% holiday allowance and 83% year-end allowance. The UFO profile Onderzoeker 4 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.

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. A prominent research topic at the UvA is Artificial Intelligence.

The UvA is part of the AI Technology for People initiative where it teams up with several other key players within the Amsterdam region. Together they will invest 1 billion euros in the development of responsible AI technologies over the next ten years by setting up research programmes attracting top scientists and educating students with state-of-the-art knowledge of AI. The UvA was selected by the European Laboratory for Learning and Intelligent Systems (ELLIS) as an Excellence Centre for AI to help keep in Europe talent in machine learning and related AI research fields.

The UvA is also involved in various labs of the Innovation Centre for AI (ICAI) which promotes public-private partnerships in the general area of AI. One of these ICAI labs is the Mercury Machine Learning this lab researchers from the University of Amsterdam (UvA) will be working together with on various improved recommendation systems. The collaboration provides the unique opportunity to be inspired by and test AI techniques in the real world allowing new machine learning methods to be safely developed for a wide range of applications for example in mobility energy or healthcare.

More information about the Mercury Machine Learning Lab and the related projects can be found on the MMLL website.

Want to know more about our organisation Read more aboutworking at the University of Amsterdam.

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. We accept applications until and including 9 July 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;
• a list of publications;
• the names and email addresses of two references who can provide letters of recommendation.

A knowledge security check can be part of the selection procedure.
(for details:national knowledge security guidelines)

Only complete applications received within the response period via the link below will be considered.

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

• Maarten de Rijke Professor of AI and Information Retrieval at the University of Amsterdam (UvA) T: 31
• Onno Zoeter Head of Booking AI Research