descrizione del lavoro

The Ubiquitous Internet Unit of IIT-CNR (Pisa, Italy) is scouting for talented researchers (post-doc level). We are collecting expressions of interest for the following research topic:Causal AI in pervasive systemsThe position is open at postdoctoral level, with the specific research direction adaptable to the candidate’s expertise. Applicants should have a strong foundation in AI/ML, causal inference.Candidate profileMSc or PhD in Computer Science, MathematicsProficiency in programming (e.g., Python, RL frameworks)Expertise in AI/Machine LearningIIT-CNR will open a formal call for the position. The scouting process is intended to advertise the above topic in view of the call. On the research topicTraditional machine learning and deep learning approaches primarily focus on correlation-based learning, identifying statistical associations between variables. However, to enable more robust, explainable, and human-centric AI, the next step is to shift from learning mere correlations to discovering causal relationships.This research aims to establish a synergy between heterogeneous electronic devices—including smartphones, wearables, IoT devices, and virtual assistants—and causal explainable AI. By leveraging our hyperconnected environments, we seek to design and deploy decentralized, human-centric causal learning frameworks that can set up and analyze causal experiments in real-world settings.The target applications will focus on pervasive systems, exploring how causal intelligence can enhance decision-making, adaptive learning, and autonomous system behavior. One key area of interest is Causal Reinforcement Learning (CRL), which extends standard reinforcement learning by enabling agents to understand cause-and-effect relationships rather than just learning from rewards. CRL can significantly improve decision-making under uncertainty, leading to AI systems that are more robust, sample-efficient, and interpretable, which is crucial for pervasive AI applications operating in dynamic real-world environments.Depending on the expertise and interests of the candidate, research activities may include:Theoretical modeling of causal inference in AI.Algorithm and system design for deploying causal learning on pervasive devices.Exploration of Causal Reinforcement Learning to improve adaptive decision-making in uncertain environments.Performance evaluation through experiments, large-scale simulations, and real-world analysis.Funding and partnershipsThe activities of this topic will be supported by FAIR: Extended Partnership on Artificial Intelligence (funded by the National Recovery and Resilience Plan (NRRP), European Union - NextGenerationEU).Further information: c.boldrini@iit.cnr.it