{"id":12648,"date":"2026-09-16T09:00:07","date_gmt":"2026-09-16T07:00:07","guid":{"rendered":"https:\/\/talentimpulse.cea.fr\/offre-emploi\/exploration-de-laposespace-des-configurations-atomiques-par-ia-generative-pour-la-simulation-des-materiaux-nucleaires-chimiquement-desordonnes\/"},"modified":"2026-11-16T18:45:17","modified_gmt":"2026-11-16T17:45:17","slug":"exploration-de-laposespace-des-configurations-atomiques-par-ia-generative-pour-la-simulation-des-materiaux-nucleaires-chimiquement-desordonnes","status":"publish","type":"offre-emploi","link":"https:\/\/talentimpulse.cea.fr\/en\/offre-emploi\/exploration-de-laposespace-des-configurations-atomiques-par-ia-generative-pour-la-simulation-des-materiaux-nucleaires-chimiquement-desordonnes\/","title":{"rendered":"Exploring the atomic configuration space with generative AI for the simulation of chemically disordered nuclear materials"},"content":{"rendered":"<p>How do you predict a materialapos;s properties when the number of possible atomic configurations exceeds 2^2500? That is the bottleneck our IRESNE (nuclear fuel physics) and LIST (AI) teams have just cracked with PULSE, a generative (VAE) method published in Nature Scientific Reports, already cutting computational cost by more than two orders of magnitude (22,282 CPU hours down to 85 on a test case). With no known equivalent in the international literature, PULSE positions CEA as a pioneer in generative sampling of the configuration space of chemically disordered materials. This 24-month postdoc gives you the opportunity to drive this method toward its next generation, leading three ambitious, parallel research axes: pushing model accuracy on systems of several thousand atoms with an IWAE architecture; equipping it with the ability to quantify its own uncertainty \u2014 a prerequisite for any use in nuclear safety; and, in the second year, tackling a high-value exploratory axis \u2014 generalizing PULSE to a continuous latent space, opening the door to any disordered crystal or alloy. You will work at the heart of an all-CEA consortium bringing together two complementary strengths \u2014 atomistic nuclear fuel physics at IRESNE and state-of-the-art generative AI at LIST \u2014 with access to CEA supercomputers, the freedom to publish in top-tier journals, and the prospect of seeing your results feed directly into reactor safety analyses through the PLEIADES platform. A position built for a curious mind who wants to combine cutting-edge generative AI research with concrete impact on a strategic nuclear-energy challenge.<\/p>","protected":false},"featured_media":0,"template":"","categories":[186],"tags":[],"class_list":["post-12648","offre-emploi","type-offre-emploi","status-publish","hentry","category-instrumentation-nucleaire-et-metrologie-des-rayonnements-ionisants"],"acf":[],"aioseo_notices":[],"_links":{"self":[{"href":"https:\/\/talentimpulse.cea.fr\/en\/wp-json\/wp\/v2\/offre-emploi\/12648","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/talentimpulse.cea.fr\/en\/wp-json\/wp\/v2\/offre-emploi"}],"about":[{"href":"https:\/\/talentimpulse.cea.fr\/en\/wp-json\/wp\/v2\/types\/offre-emploi"}],"wp:attachment":[{"href":"https:\/\/talentimpulse.cea.fr\/en\/wp-json\/wp\/v2\/media?parent=12648"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/talentimpulse.cea.fr\/en\/wp-json\/wp\/v2\/categories?post=12648"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/talentimpulse.cea.fr\/en\/wp-json\/wp\/v2\/tags?post=12648"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}