Description

As a Quantitative Developer and Data Scientist with a robust background in applied mathematics, computer science, and finance, I offer expertise in developing advanced financial models and data-driven solutions. Currently pursuing a Master of Engineering at CY Cergy Paris Université, I have hands-on experience in modeling portfolio default correlations, simulating macroeconomic shocks, and implementing hedging strategies. Proficient in Python, C++, and various data science frameworks, I have successfully contributed to projects at Bpifrance and Letxbe AI, enhancing model performance and accuracy. My skills in quantitative modeling, financial engineering, and data science, combined with fluency in English and native proficiency in French, enable me to deliver high-quality solutions and insights for complex challenges.

Domaines d’expertise

Langues

Français
Bilingue ou natif
Anglais
Bilingue ou natif

Préférences en matière de lieu de travail

Accepte de travailler sur site

Paris (jusqu’à 50 km)

Bpifrance
Quantitative developer
CAPITAL-INVESTISSEMENT
septembre 2023 - Aujourd'hui (2 ans et 9 mois)
Paris, France
Reduced runtime and improved maintainability by migrating guaranty model from SAS to Python.
Modeled portfolio default correlations using Gaussian and Student-t copulas (MLE & Kendall’s τ).
Simulated correlated macroeconomic shocks (GDP, yield curves, inflation) to assess credit loss impact and portfolio VaR under reverse
stress testing scenarios.
Capital Forecasting Model to estimate the Leverage Ratio for equity guarantees by incorporating key Macro Risk Drivers.
Developed quantile-based backtesting framework for Economic Capital and Funding models, improving model validation and risk
accuracy.
Python Quantitative Finance Risque de crédit Modélisation mathématique Pricing
Letxbe AI
Data Scientist
janvier 2023 - janvier 2023
Developed a system to detect charts indicating the presence of asbestos in documents.
Applied Natural Language Processing (NLP) techniques to extract and analyze textual context.
Utilized machine learning models including XGBoost, Multilayer Perceptron (MLP), and Random Forest for classification tasks.
XGBoost Machine learning Python Scikit-learn