A postdoctoral position is available in the relational cognition lab <https://urldefense.com/v3/__https://www.relcoglab.org/__;!!CzAuKJ42GuquVTTmV...> at UC Irvine, directed by Anna Leshinskaya. The position is funded by a 2-year grant from the Schmidt Sciences AI Safety Science Program <https://urldefense.com/v3/__https://www.schmidtsciences.org/safetyscience/__...> , co-led with collaborators Seth Lazar and Alice Oh. The project involves developing experiments and interpretable computational models of morally guided decision-making and conceptual combinatorial thought in humans and large language models. Applicants should have a background in computational cognitive science and ideally, AI interpretability, with strengths in research project design and leadership, collaboration and mentorship, and python skills for working with research code repositories and with large language models. ML experience not required, but familiarity with probabilistic programming and methods in neural network interpretability a plus. Background in conceptual and relational reasoning, moral cognition, and decision-making is highly relevant. The position is either fully onsite in Irvine, CA, or hybrid. Please email me at aleshins@uci.edu to express interest.