Machine Learning Engineer · PhD Engineer in Computational Fluid Dynamics
📍 Nantes, France · Actively seeking new opportunities
PhD engineer with 10 years of experience in computational fluid dynamics (CFD), naval hydrodynamics and aerodynamics, now transitioning to machine learning to broaden my scientific scope. I bridge physical modeling and data-driven approaches, with a strong interest in industrial, scientific and high-impact ML applications.
Before retraining in data science and AI, I spent a decade working at the intersection of scientific research and applied engineering. My career began with a doctoral thesis in fluid mechanics within a CNRS research laboratory, followed by an engineering position in another university research lab. I then moved to industry, joining a deep-tech startup specializing in naval hydrodynamics, and most recently worked as a consulting CFD engineer on industrial wind-propulsion and aerodynamic projects. Across these roles, I developed CFD algorithms, automated complex simulation workflows in Python, validated numerical models against experimental data, and collaborated with multidisciplinary teams on R&D projects.
In early 2026, I completed an intensive 3-month bootcamp in Data Science and Data Engineering at Jedha, leading to the French RNCP Level 6 certification Machine Learning Engineer (equivalent to a Bachelor's level qualification in the French national framework). The program covered supervised and unsupervised machine learning, deep learning, big data processing with PySpark, ML deployment (MLflow, Docker, FastAPI), and large language models. I validated the six certification blocks through eight individual projects and one group capstone, applying the full ML lifecycle from data collection to production deployment.
| Block | Project | Key Competencies | Tech Stack |
|---|---|---|---|
| 1 | Kayak — destination & hotel recommendation pipeline | Data engineering (ETL) | Scrapy · AWS S3 · AWS RDS PostgreSQL · SQLAlchemy |
| 2 | Steam — drivers of video-game success | EDA (big data) | PySpark · Databricks |
| 2 | Tinder — what motivates a second date | EDA | pandas · Plotly · statsmodels |
| 3 | Conversion Rate Challenge — newsletter subscription prediction | Supervised ML (classification) | scikit-learn · XGBoost · Plotly |
| 3 | Uber Pickups — demand hot zones in New York | Unsupervised ML (clustering) | scikit-learn · GeoPandas · Plotly |
| 3 | Walmart Sales — weekly revenue prediction | Supervised ML (regression) | scikit-learn · pandas · Plotly |
| 4 | AT&T Spam Detector — SMS spam vs ham classification | Deep learning (NLP) | PyTorch · Hugging Face Transformers · tiktoken |
| 5 | Getaround Analysis — rental threshold & daily-price prediction | ML industrialization (MLOps) | FastAPI · MLflow · Docker · Hugging Face Spaces |
| 6 | RTE Project — electricity consumption forecasting in France | Data project management | Prophet · AWS S3 · AWS EC2 · Streamlit |
Languages
Machine Learning & Deep Learning
Data Engineering & Big Data
MLOps & Deployment
Cloud & Databases
Visualization & Apps
Tools
I have authored several peer-reviewed publications in computational fluid dynamics during my academic career. The full list is available on my ResearchGate profile.
Currently looking for Machine Learning Engineer positions on-site in Nantes or hybrid in Paris, with a focus on generalist ML roles or applications to physical, industrial, sports or renewable-energy domains.