Particle Physics AI Engineer — Data Processing & HL-LHC ML

CEA; Gif-sur-Yvette; Sur place; EUR 65 000 - 95 000; Plein temps

Résumé du poste

CEA is recruiting an Data Processing/AI Engineer to develop AI models for particle physics, addressing HL‑LHC data challenges at Saclay. You will work with physicists, computing engineers and ML researchers to advance event reconstruction and physics analysis.

The role focuses on self-supervised learning on simulated and real data, building data pipelines, and contributing to publications and presentations at international conferences.

Qualifications

• PhD in computational physics, signal processing/AI or related field.
• Good knowledge of particle physics and/or nuclear physics.
• Strong background in large-scale data processing and ML/DL (neural networks, transformers).
• Proficiency with Python AI/ML frameworks (PyTorch) and scientific Python ecosystem (NumPy, Pandas, Scikit-learn).
• Experience with Git and CI/CD for collaborative software development.
• Experience with HPC environments (GPU clusters, SLURM).

Responsabilités

• Design, train and evaluate AI model architectures for particle physics data.
• Develop self-supervised learning strategies using simulated and real LHC datasets.
• Create data processing pipelines, experiment tracking tools and physics benchmarks.
• Contribute to scientific and technical documentation, publications and international conference presentations.

Connaissances

Python

PyTorch

Machine learning

Deep learning

Data processing

HPC

Formation

PhD in computational physics

Particle/nuclear physics knowledge

Outils

Git

CI/CD

SciPy stack (NumPy/Pandas/Scikit-learn)

ROOT

Description du poste

CEA is recruiting an Data Processing/AI Engineer to develop AI models for particle physics, addressing HL‑LHC data challenges at Saclay. You will work with physicists, computing engineers and ML researchers to advance event reconstruction and physics analysis.

The role focuses on self-supervised learning on simulated and real data, building data pipelines, and contributing to publications and presentations at international conferences.