AI/ML Engineer.
I am an AI/ML Engineer specializing in high-performance retrieval pipelines and machine learning systems. Backed by a Master’s degree in Applied Econometrics and a Diploma in Artificial Intelligence from La Cité, I focus on transitioning complex quantitative models and data architectures into production-ready deployments.
My background bridges rigorous statistical inference and modern AI engineering, allowing me to build solutions that are not just technically advanced, but mathematically sound and aligned with real-world business logic.
Four pillars of practice.
Statistical Communication
Eight years as an Economics & Statistics educator. I translate complex econometric theories, causal inferences, and predictive models into clear, actionable insights for both technical and non-technical audiences.
Predictive Analytics
End-to-end geospatial valuation models using supervised ensemble methods (XGBoost, CatBoost). Rigorous hypothesis testing and feature engineering across 80+ structural and geospatial variables.
Quantitative AI Evaluation
Mathematical benchmarking pipelines for Large Language Model outputs using the RAGAS framework. Cross-encoder abstention mechanisms designed to mathematically prevent hallucinations in enterprise architectures.
High-Dimensional Optimization
Fine-tuning of deep learning models (Matryoshka embeddings) on the Amazon ESCI dataset. Compressed embedding dimensions while maintaining strict recall and nDCG performance metrics.