We are seeking candidates in the field of Mathematics for Responsible Artificial Intelligence (RAI). RAI is an interdisciplinary effort to develop AI systems that are fair, accountable, transparent, and socially considerate. The growing adoption of advanced AI technologies has highlighted the importance of addressing ethical, legal, and societal concerns. Despite the need for responsible AI, it is estimated that most technical AI research focuses on increasing the AI capabilities, with only a very small fraction dedicated to AI safety. The research of the new assistant professor tenure track (APTT) will focus on the mathematics of responsible and trustworthy AI. The professorship will be embedded in the Department of Mathematical Modeling and Machine Learning (DM3L) and concentrates on devising mathematical foundations and principles to enhance the accountability, transparency and explainability, fairness and non-discrimination, of AI systems. More specifically (but not exclusively), we seek candidates with competences around the following pillars (i) accountability: developing systems where algorithmic decisions can be traced and audited; ensuring that outcomes are verifiable against standards and rules; (ii) transparency and explainability: creating interpretable models where the decision process is clear; (iii) fairness and non-discrimination: designing algorithms to make unbiased decisions by mathematically defining fairness (e.g., demographic parity, equality of opportunity), and integrating these definitions into model optimization and evaluation processes (hereby acknowledging the complications of algorithmic notions of fairness); (iv) AI alignment : developing AI models that operate in a way that is consistent with human goals, intentions, and values. The professorship will focus on a deeper mathematical understanding of accuracy, explainability, mitigation of bias, reliability, and robustness of RAI.
In your application, please refer to Professorpositions.com