PhD candidate in Methodology & Statistics

Do you want to conduct cutting-edge AI research within a large ERC Synergy project addressing one of the most pressing human rights challenges worldwide?

This position offers a rare opportunity to conduct high-impact research at the intersection of artificial intelligence and psychological science within a large, internationally visible research programme.

Your position
This 4-year, fully-funded PhD project is part of the ERC Synergy Grant JUSTICE – Joining Unique Strategies Together for Interrogative Coercion Elimination.

The position focuses on the development, alignment, and evaluation of generative language models designed to support ethical, human rights-compliant investigative interviewing. Recent advances in AI have created unprecedented opportunities to model complex conversational behaviour. This project pushes the boundaries of current AI systems by incorporating reinforcement learning and adaptive model optimisation, addressing a fundamental scientific challenge: how highly flexible generative models can be aligned with explicit ethical constraints in complex conversational settings. The project offers substantial intellectual freedom and requires a high degree of independent problem-solving.

The PhD candidate will join the Computational Psychology and Computational Methods Lab (CPCM Lab, cpcm-lab.net), an internationally oriented research group dedicated to advancing computational approaches to understanding human behaviour. The lab integrates machine learning, generative language models, behavioural science, and statistical modelling within an intellectually ambitious and methodologically rigorous research environment. Embedding within the CPCM Lab provides an excellent foundation for an academic career or a career in the AI industry, with opportunities for international collaboration and research internships.

The project will be supervised by Dr. Bennett Kleinberg.

Your responsibilities:

• Develop and adapt large language model pipelines
• Design alignment and norm-constrained modelling strategies
• Implement model evaluation and reinforcement learning workflows
• Analyse theoretical and empirical model behaviour
• Publish in international peer-reviewed journals or conference proceedings
• Present at leading conferences
• Write a doctoral dissertation
• Contribute to Open Science and collaborative research
• Participate actively in the JUSTICE project
• Participate in the CPCM Lab and the Department of Methodology & Statistics
• Contribute modestly to teaching (max. 10%)

Background
Large language models are transforming how we study language, human psychology, and decision-making. Yet their behaviour in ethically sensitive, high-stakes contexts remains poorly understood. Investigative interviewing provides a uniquely demanding test case for norm-constrained AI. The project explores how AI systems can be designed through self-learning to operate within explicit human rights frameworks (e.g., the Mendez Principles of investigative interviewing) - a challenge at the frontier of machine learning and behavioural science.

About the JUSTICE project

JUSTICE (Joining Unique Strategies Together for Interrogative Coercion Elimination) is a major ERC Synergy project funded for six years with more than EUR 10m. The project addresses one of the most pressing challenges in global justice systems: the persistence of coercive and abusive interrogation practices. By integrating artificial intelligence, data science, psychology, neuroscience, criminal law, and policing research, JUSTICE develops evidence-based strategies for ethical, human rights-compliant investigative interviewing and establishes a new scientific frontier at the intersection of human decision-making and AI.

The project is led by four principal investigators: Bennett Kleinberg (Tilburg University), Shane O’Mara (Trinity College Dublin), Yvonne Daly (Dublin City University), and Dave Walsh (De Montfort University). Researchers hired within JUSTICE benefit from a uniquely interdisciplinary and international research network.

We are looking for candidates with a background in Machine Learning, Artificial Intelligence, NLP, Data Science, Computer Science, Statistics, Mathematics, Computational Linguistics, Psychometrics, or related fields.

Requirements

• (Nearly) completed Master’s degree
• Strong Python / programming skills
• Solid foundation in machine learning or statistical modelling
• Experience with NLP and/or deep learning methods
• Interest in LLMs / generative language models
• Interest in psychological research
• Strong analytical and statistical skills
• Interest in interdisciplinary research
• Proficiency in English

Experience with LLMs or reinforcement learning is advantageous but not required.

The position involves methodological and computational model development rather than the mere application of existing models. The ideal candidate should therefore have a strong interest in machine learning fundamentals and be comfortable working with technically demanding machine learning concepts. The project ensures sufficient computational infrastructure for ambitious model development.

This position is also suitable for candidates with a background in the social and behavioural sciences if they have a strong background in statistics and computational methods.

We particularly encourage applications from candidates who enjoy tackling open-ended research problems and developing novel modelling approaches.

Our offer
Tilburg University offers excellent benefits in a pleasant working environment:

• A position based on 1.0 fte (40 hours per week).
• A salary of minimum €3.059 and maximum €3.881gross per month for full-time employment, based on UFO profile PhD and salary scale PhD. Tilburg University uses a neutral remuneration system based on relevant work experience.
• This is a vacancy for for a PhD in accordance with Article 2.3 paragraph 8 sub b CLA DU. You will initially be given a temporary contract for the duration of 12 months.
• Vacation pay of 8% and a year-end bonus of 8.3%.
• Over 8 weeks of vacation leave.
• The opportunity to work partly on campus and partly from home with a home office allowance of €2 per day.
• Reimbursement for sustainable commuting: walking, cycling, and public transport.
• A monthly internet allowance of €25.
• An options model in which you exchange benefits for things such as additional leave, more pension, a bicycle or personal training at our Sports Center.
• A moving allowance (subject to conditions).
• Employees from abroad may be eligible for a tax-free allowance for extraterritorial expenses equal to 30% of taxable salary.
• A pension with ABP; the largest Dutch pension fund.
• Training in personal development, career development, leadership, education, and research. Or a language course at our Language Center.
• A work culture in which we embrace differences, everyone is welcome and given equal opportunities.
• A vibrant campus in green surroundings that is easily accessible by public transport.

For more information, see our Working at Tilburg University | Tilburg University and the CLA Dutch Universities.

Tilburg University is an academic, inclusive, and engaged community. Together with nearly 3,000 employees, we are committed to broad prosperity, sustainably, and inclusion. For current and future generations. We develop and share knowledge for the requirements of people and our society. This is how we contribute to solving complex social issues and help society move forward.

We educate our 19,500 students of 110 nationalities to become responsible leaders with knowledge, skills, and character. With our education and research for broad prosperity, we exceedingly focus on themes such as mental and preventive care, an inclusive labor market, the energy transition, and digitalization.

About Tilburg School of Social and Behavioral sciences

Tilburg School of Social and Behavioral Sciences (TSB) is one of the five faculties of Tilburg University. The teaching and research of the Tilburg School of Social and Behavioral Sciences are organized around the themes of “Adaptive societies, organizations, and workers”, “Healthy life span”, and “Personalized prevention and care”. The School’s inspiring working environment challenges its workers to realize their ambitions, involvement and cooperation are essential to achieve this.   
Tilburg School of Social and Behavioral Sciences | Tilburg University

Department Methodology and Statistics

The Department of Methodology and Statistics is responsible for education and research in methodology and statistics for the social and behavioral sciences. Methodology and statistics play an essential role in all subfields of the social and behavioral sciences, and related fields including data science and artificial intelligence. At the Department of Methodology and Statistics, we do research on and teach about computational, quantitative and qualitative methods that researchers need in order to answer challenging research questions, come up with strong research designs, critically apply statistical analyses, and avoid bias when interpreting research findings. Within the department, there is a strong focus on developing novel statistical and methodological techniques to tackle complex problems in the social and behavioral sciences.

Link to our website: Department Methodology and Statistics | Tilburg University

Want to know more?

Would you like to know more before applying? Feel free to contact Dr Bennett Kleinberg at bennett.Kleinberg@tilburguniversity.edu