Description

PhD en Machine Learning avec 7 ans d'expertise, un solide background en R&D et des expériences en startups, freelancing et gestion d'équipe, prêt à concrétiser vos projets IA les plus innovants.

Après un doctorat au sein du premier institut de recherche en IA en Australie, j’ai dirigé une équipe de 3 data scientists sur divers projets. Pendant mon doctorat, j’ai également travaillé sur plusieurs missions freelance, notamment avec TotalEnergies et Naval Group Pacific en Australie. Avant cela, j’ai acquis une expérience significative dans une startup deep tech, où j’ai appliqué le Reinforcement Learning pour l'optimisation logistique.

Mon expertise couvre des domaines tels que Reinforcement Learning, Causal Inference, Computer Vision, Predictive Analysis, Generative AI et Graph Neural Networks, soutenue par un fort background en mathématiques. J’ai également une solide expérience dans l'intégration et la mise en production de solutions basées sur Azure.

Je suis prêt à accompagner vos projets IA à chaque étape, de la modélisation à la mise en production.

Languages

French
Native or bilingual
English
Native or bilingual
Arabic
Native or bilingual

Workplace preferences

Can work on-site

Paris (up to 50km)

TotalEnergies
Applied Scientist
January 2025 - December 2025 (11 months)
- Worked with stakeholders to translate key business challenges (like EV flexibility and Microgrid optimization) into practical, high-impact Reinforcement Learning (RL) use cases.
- Designed and developed an RL simulation framework to train trading strategies for optimizing energy procurement for EV truck fleets on both the Day-Ahead (DA) and Continuous Intraday (CID) european markets.
- Trained RL agents to dynamically correct Day-Ahead positions with intraday trades based on updated forecasts to reduce the total energy procurement cost while respecting operational constraints.
- Demonstrated 30%+ total energy cost reduction in extensive backtesting, validating the RL strategy's effectiveness in leveraging EV fleet flexibility.
Mantu Innovation Lab
Lead Data Scientist
November 2023 - October 2024 (11 months)
Paris, France
Led a small team of junior data scientists, demonstrating both project management and technical skills.
Designed two R&D projects and managed and contributed to their development:
(1) An energy consumption forecasting system for a smart building leveraging sensor data and focusing on time series forecasting
(2) A gait-based intrusion detection system, utilizing advanced computer vision techniques.
Azure Machine Learning Time Series Forecasting Computer Vision MLflow Pytorch
Naval Group
ML Engineer
DEFENSE AND MILITARY
July 2022 - December 2022 (6 months)
Adélaïde, Australia
Developed an explainable vessel recognition system to enhance interpretability in maritime security systems.
Implemented a Vision Transformer model with pairwise heatmap visualization using Attention Flow Approximation. This approach provided intuitive interpretation of results, matching the performance of standard CNN models while offering superior explanations compared to classic techniques like GradCam.
Computer Vision Machine learning Python