Safe Multi-Agent AI: Causal Insights

Vedi l’offerta su Go Lavoro: golavoro.it/annuncio-lavoro/78ez79

Politecnico di Milano is offering a research fellowship focusing on analyzing and ensuring the safety of AI agents in multi-agent environments. The research will investigate emergent risks and intervention mechanisms using causal inference methods and opinion dynamics models.
Eligible candidates must have relevant research activities and experience related to AI safety. The application deadline is set for July 10, 2026. This program is not funded by the EU and is open to all nationalities.
J-18808-Ljbffr

Vedi l’offerta su Go Lavoro: golavoro.it/annuncio-lavoro/78ez79