About this role
Summary: This 24-month postdoctoral position focuses on enhancing PULSE, a generative VAE method for predicting properties of chemically disordered nuclear materials. The role involves improving model accuracy, uncertainty quantification, and transitioning to a continuous latent space within a CEA consortium.
### Sujet de stage
This postdoc aims to enhance PULSE, a generative (VAE) method revolutionizing predictions for disordered materials. You'll improve its accuracy, uncertainty quantification, and transition to a continuous latent space within a CEA consortium combining nuclear physics and AI.
### Description de l'offre
How do you predict a material'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 — a prerequisite for any use in nuclear safety; and, in the second year, tackling a high-value exploratory axis — 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 — atomistic nuclear fuel physics at IRESNE and state-of-the-art generative AI at LIST — 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.
*#CEA-List ; #Research Engineer*
### Profil du candidat
You hold a PhD in Physics, Applied Mathematics, or Computer Science, with experience in deep generative models (VAE, diffusion) and Python/PyTorch.
Applications from statistical physicists are welcome.
STILL HESITATING?
The additional benefits of your mission might interest you:
- A cutting-edge research ecosystem, unique in its field and dedicated to high-impact societal themes, giving meaning to your work.
- Training programs to strengthen your skills, acquire new ones, and enhance your mission.
- A work-life balance recognized by our team members.
- Remote work options to reduce commuting time and improve your quality of life.
- A rich employee benefits committee (CE) with social, cultural, and sports activities.
- A dynamic workplace at the heart of a vibrant hub, surrounded by schools and tech companies.
Interested? Apply—this position is perfect for you!
*In line with the CEA’s commitment to inclusivity, this role is open to all. The CEA offers accommodations and/or organizational adjustments to support workers with disabilities.*