The IMDEA Software Institute invites applications for a PhD position on causality-based approaches for explainable RL. The successful candidate will join a dynamic research group working at the intersection of reinforcement learning, causal inference, and statistical methodology.
RL has emerged as a powerful paradigm for training agents to make sequential decisions in dynamic environments. However, RL systems often operate as “black boxes”, limiting their transparency and hindering their adoption in critical domains such as healthcare, finance, autonomous systems, and governance. Furthermore, this also makes it difficult to analyze the impact of their decisions on equity and fairness. This project aims to address these challenges by integrating causal reasoning into RL to provide robust and interpretable explanations of agent behavior.
Applicants should hold an MSc (or equivalent) in Statistics, Data Science, Computer Science, Mathematics, or a closely related field. A strong background in probability theory and statistical inference is expected, along with solid knowledge of machine learning, particularly RL. Foundational knowledge of causal inference (e.g., structural causal models and counterfactual reasoning) and strong programming skills in Python are also required. Prior research experience in explainable AI, RL, or causal inference is desirable.
The position is based in Madrid, Spain, where the IMDEA Software Institute is situated. The institute provides for travel expenses and an internationally competitive stipend. The working language at the institute is English.
Applicants interested in the position should submit their application at https://careers.software.imdea.org/ using reference code 2026-04-phd-causality. Deadline for applications is April 16th, 2026. Review of applications will begin immediately.
The recruitment process will comply with the IMDEA Software Institute’s OTM-R Policy (Open, Transparent and Merit-based Recruitment).
For enquiries about the position, please contact Antonio Fernández ().
