Christophe Marabotto

About

Over the past five years, I have been operating at the intersection of Deep Learning research and industry, particularly in the aeronautics and space domains, working on Computer Vision, neural network optimization for on-board deployment, and Natural Language Processing.

My current research interests include AI for robotics, with emphasis on foundation models for perception and energy-efficient architectures, targeting demanding applications in medical robotics, defense, sustainability, and autonomous systems.

Education

• Diplôme d’ingénieur – EPITA, Paris, France (2018–2021)
  Specialized in Data Science and Artificial Intelligence (SCIA).
  Main subjects: Mathematics, Algorithmics, and Data Science.
• Preparatory Classes (PCSI/PSI) – Lycée Alphonse Daudet, Nîmes, France (2016–2018)
  Main subjects: Mathematics, Physics, and Engineering Sciences.

Work Experience

• AI Research Engineer – IRT Saint Exupéry, Toulouse, France (2021–now)
  • AIxIA (Artificial Intelligence for Interference Analysis) – Ongoing
    PM acting: Coordination of activities.
    Leading the development of explainable language-based approaches for interference identification on multi-core processors.
  • RAKEL (Robust and Accurate Knowledge Extraction by LLM) – Ongoing
    Hallucination Detection for NOTAM Classification.
  • RAPTOR (Robotic and Artificial Intelligence Processing Test On Representative Target) – 3 years (70%)
    Leading the development of deep learning models for non-cooperative spacecraft rendezvous missions (Pose Estimation).
    Design of a synthetic dataset. Optimization and deployment on space flight hardware.
  • Confiance.ai (Grand Défi "Securing, certifying and enhancing the reliability of systems based on artificial intelligence") – 3 years (30%)
    Development of a test bench for optimizing and evaluating neural networks on FPGAs using Vitis AI (AMD).
    Study of semantic preservation for AI certification.
• Data Scientist – Airbus Defence and Space, Sophia Antipolis, France (End-of-studies Internship, 6 months, 2021)
  Semantic segmentation of very high-resolution satellite images using Deep Learning within an Agile team.
• End-of-study Project – ipso santé, Paris, France (2020–2021)
  Unsupervised clustering of medical reports using Topic Modelling techniques with a team of 4.
• Data Scientist – Hexaglobe, Paris, France (Internship, 5 months, 2019–2020)
  Anomaly detection using Deep Learning for a streaming service for both marketing analysis and breakdown prediction using Keras, Kafka, and Google Cloud Platform.

Public Scientific Communication

• On-board AI for Critical Applications, C. Marabotto, Robotop’IA 2025 / Workshop LIRMM. [pdf]
• An Evaluation Bench for the Exploration of Machine Learning Deployment Solutions on Embedded Platforms, E. Jenn et al., ERTS 2024. [pdf]
• Exploring AI-Based Satellite Pose Estimation: from Novel Synthetic Dataset to In-Depth Performance Evaluation, F. Gallet et al., CVPRW 2024 (AI4Space). [pdf]