Postdoctoral Researcher – Deep Learning for Oxide Growth Prediction

About the role

We are seeking a highly motivated Postdoctoral Researcher to develop deep‑learning models that predict the X‑ray Diffraction (XRD) spectrum of functional‑oxide thin films directly from Reflection High‑Energy Electron Diffraction (RHEED) videos recorded during Molecular Beam Epitaxy growth. The role sits at the interface of artificial intelligence and materials physics within the OXYD‑IA project at École Centrale de Lyon.

Key responsibilities

• Build and curate a versioned RHEED/XRD dataset, aligning video sequences with MBE parameters and ex‑situ spectra.
• Design and train spatio‑temporal video encoders (e.g., 3D CNNs, Vision Transformers) and probabilistic regression models to predict structural parameters and full XRD spectra with calibrated uncertainty.
• Validate models on new growths, prototype a real‑time inference tool, and contribute to joint high‑impact publications.

Required profile

• Ph.D. in AI, Computer Science, Machine Learning, Computer Vision or Signal Processing with 2–5 years post‑PhD experience.
• Hands‑on experience with deep learning on video data (3D CNNs, temporal transformers) and proficiency in Python and PyTorch or TensorFlow.
• Strong interest in experimental physics or materials science and a proven research track record.

Required skills

• Python programming
• PyTorch or TensorFlow
• 3D CNNs / temporal Vision Transformers
• Probabilistic modelling and uncertainty quantification (Bayesian methods, deep ensembles)
• Git version control