SD-27033 RESEARCH SCIENTIST IN GAME THEORY FOR MULTI-AGENT AI GOVERNANCE
Fixed term contract | Belval | 24 Months
Are you passionate about research? So are we! Come and join us
The Luxembourg Institute of Science and Technology (LIST) is a leading Research and Technology Organisation (RTO) that drives innovation for the economy and society in Luxembourg and beyond. With cutting-edge expertise in Natural, Built, Industrial environments, Space, AI, Security and defence technologies. LIST bridges scientific excellence and applied research to design solutions that address real-world challenges and create positive impact.
Do you want to know more about LIST? Check our website: https://www.list.lu/
How will you contribute?
You will join the AI Readiness and Assessment (AIRA) group of LIST’s Human-centered AI, Data and Software (HANDS) unit as the main researcher of AI-LIGNMENT, a 24-month project funded by the Luxembourg National Research Fund (FNR) under the CORE programme.
AI is shifting from systems that answer prompts to agents that plan, decide and act, increasingly combined into multi-agent systems whose behaviour emerges from interaction rather than from any single model. This strains the human oversight, transparency and explainability that the EU AI Act requires. AI-LIGNMENT responds with a governance framework grounded in game theory: it translates regulatory and organisational requirements into a machine-readable admissible action space, interprets collective agent behaviour as trajectories in that space, detects drift towards undesirable regimes before violations occur, and recalibrates incentives, communication, agent identities and information conditions under human oversight.
Working closely with the Principal Investigator, a research engineer and an academic mentor from the University of Cambridge, you will be mainly in charge of:
• Formalising alignment and explainability as system-level properties of interaction dynamics in LLM-based multi-agent systems, across collaborative, competitive and parallel-execution architectures.
• Developing a conceptual and formal model that translates regulatory, organisational and domain-specific requirements (notably the EU AI Act) into a machine-readable admissible action space, in connection with a domain-specific language.
• Formalising the observation–evaluation–recalibration governance loop with game-theoretic concepts: trajectory-based evaluation, regime stability, equilibrium selection and early detection of directional drift.
• Designing and running controlled, reproducible experiments and simulations with LLM-based agents to test the project hypotheses and validate system-level indicators.
• Contributing, together with the project’s research engineer, to the research prototype: specifying and implementing the game-theoretic analysis module and the recalibration engine that adjusts incentives, communication and identity parameters.
• Validating the framework and prototype on a use case drawn from public administration, through baseline and recalibration experiments, and analysing their effects on system trajectories, compliance and robustness.
• Publishing your results in leading journals and conferences (e.g. IJCAI, ECAI, AIJ, JAIR, FAccT, AIES), presenting them to the research community, and contributing to the open-source release of the framework with its data and reproducibility artefacts.
• Contributing to project deliverables and reports, exchanging with regulatory authorities and public and private partners, supporting PhD students and trainees working on related topics, and helping to identify and prepare new funding opportunities.
Is Your profile described below? Are you our future colleague? Apply now!
Education
• PhD in Computer Science, Artificial Intelligence, Applied Mathematics, or a closely related field.
Experience and skills
• Research experience in game theory and/or multi-agent systems acquired during the PhD;
• Strong mathematical foundations in game theory (equilibrium analysis and selection, repeated and evolutionary games, mechanism design), probability and statistics.
• Experience in modelling, simulating and analysing multi-agent systems; hands-on experience with LLM-based agents or agentic frameworks is a strong asset.
• Solid programming skills in Python and scientific computing, with good practices for reproducible research (version control, documented experiments).
• A publication record in recognised international venues, commensurate with your career stage.
• Knowledge of AI alignment and safety, explainability, AI governance or the EU AI Act, and of domain-specific languages or model-driven engineering, is an asset.
• Good project management skills: you organise your work autonomously to meet objectives and deadlines; knowledge of research funding and an interest in contributing to project proposals are a plus.
• Team spirit, scientific rigour and critical thinking, with clear communication and presentation skills towards both scientific and non-technical audiences (e.g. regulators and public administrations).
Language skills
• Fluency in English, both oral and written.
• French or German languages are an asset.
Your LIST benefits
· An organisation with a passion for impact and strong RDI partnerships in Luxembourg and Europe that works on responsible and independent research projects
· Sustainable by design, empowering our belief that we play an essential role in paving the way to a green society
· Innovative infrastructures and exceptional labs occupying more than 5,000 square metres, including innovations in all that we do
· An environment encouraging curiosity, innovation and entrepreneurship in all areas
· Personalised learning programme to foster our staff’s soft and technical skills
· Multicultural and international work environment with more than 60 nationalities represented in our workforce
· Diverse and inclusive work environment empowering our people to fulfil their personal and professional ambitions
· Gender-friendly environment with multiple actions to attract, develop and retain women in science
· 32 days’ paid annual leave, 11 public holidays, 13-month salary, statutory health insurance
· Flexible working hours, home working policy (not remote) and access to Digital lunch vouchers
Apply online
Your application must include:
· A motivation letter oriented towards the position and detailing your experience
· A scientific CV with contact details
· List of publications (and patents, if applicable)
· Contact details of 2 references
Please apply ONLINE formally through the HR system. Applications by email will not be considered.
Application procedure and conditions
We kindly request applicants to provide their nationality for statistical purposes only, as part of our commitment to promoting diversity and ensuring equal opportunities in our workforce. This information will be kept confidential and will not be used for any discriminatory purposes.
LIST is dedicated to maintaining an inclusive work environment and is an equal opportunity employer. We are committed to attracting, hiring, and retaining a diverse workforce. All applicants will be considered for employment without discrimination based on national origin, race, ethnicity, gender, sexual orientation, gender identity, marital status, religion, age, or disability.
Applications will be continuously reviewed until the position is filled. An assessment committee will thoroughly evaluate applications, adhering to guidelines designed to ensure equal opportunities. The primary criteria for selection will be the alignment of the applicant's existing skills and expertise with the requirements mentioned above.
As part of our recruitment process, the selected candidate might be subject to a background check in accordance with applicable laws and institutional policies. Further checks and restrictions might apply to candidates in compliance with export controls requirements
For the purposes of the position and in accordance with applicable legislation, the successful candidate may be requested to provide a recent criminal record certificate.
This position offers a gross monthly salary between €6094 and €6678, paid over 13 months (€79.222–€86.814 annually) based on full‑time employment. The final salary offer within this range will be determined based on the candidate’s overall profile, qualifications and professional experience.
For part‑time employment, the salary is adjusted pro rata.
Informationen
SD-27033 RESEARCH SCIENTIST IN GAME THEORY FOR MULTI-AGENT AI GOVERNANCE
Befristet (CDD)
19.11.2026
Esch-Sur-Alzette
Doktortitel
Vollzeit

