Postdoc in computational social choice for AI Safety
A 2-year postdoc position in computational social choice for AI Safety is available at the Bernoulli Institute for Mathematics, Computer Science and Artificial Intelligence of the University of Groningen in The Netherlands.
The position is available within the research project "Aggregating Safety Prefer-ences for AI Systems: A Social Choice Approach." The project aims to develop formal methods for eliciting and aggregating safety specifications and risk thresh-olds for AI systems, with a particular focus on mechanisms that provide axiomatic guarantees, are algorithmically tractable, and show good performance in computa-tional experiments. The project's research outcomes are expected to contribute to the design of safeguarded AI systems that reflect diverse stakeholder prefer-ences. This project is funded by the Advanced Research + Invention Agency (ARIA) as part of their Safeguarded AI program that aims to develop the safety standards needed for transformational AI. The successful candidate would become an ARIA R&D creator.
Responsibilities:
- Conduct foundational research on aggregation mechanisms, including: for-mal modeling and axiomatic analysis, computational complexity and algo-rithmic properties, and experimental evaluation in testbeds.
- Collaborate actively with co-Creators (maybe add university names here?) and engage in project-related activities.
- Disseminate research findings at leading international conferences and journals.
Knowledge of the Dutch language is not required.
Organisation
Since its foundation in 1614, the University of Groningen has enjoyed an international reputation as a dynamic and innovative centre of higher education offering high-quality teaching and research. Balanced study and career paths in a wide variety of disciplines encourage currently more than 34,000 students and researchers to develop their own individual talents. Belonging to the best research universities in Europe and the top 100 universities in the world, the University of Groningen is truly an international place of knowledge.
Within the Faculty of Science and Engineering (FSE), the Bernoulli Institute conducts research combining theoretical as well as practical aspects of three disciplines, namely Mathematics, Computer Science and Artificial Intelligence. The position is embedded in the Multi-Agent Systems group of the department of Artificial Intelligence of the Bernoulli Institute.
