Professional Journey

From quantitative finance in Paris to leading AI engineering teams — building systems that demand both mathematical rigor and real-world impact.

Dec 2024 — Present
Lead Generative AI Engineer
Servier Laboratory — ClinDev
Agentic ICFVision RAGDSPyWeaviateDocling
Agentic ICF Generator — Transforms Clinical Study Protocol tables into ICF Summary Tables using Skills Cards architecture with scoped MCP tool restrictions. 1–2 days manual → under 60 sec.
Vision Agentic RAG — Multimodal retrieval system with DSPy serving a global medical writing team. Retrieval hit-rate@6: 60% → 85% across thousands of documents and images.
Custom Document Parser — Docling-based parser extracting tables, figures, and images from PDFs, RTF, DOCX into structured Markdown; indexed into Weaviate + GCS.
Apr 2024 — Nov 2024
Lead Data Scientist
KPMG — Audit Department
RAG ChatbotDSPy OptimizersAzure SearchLangFuse
Compound AI Audit Chatbot — Led team of 5, delivered POC in 2 months and production-ready chatbot in 3 months, parsing thousands of documents (PDF, PPTX, images). Answer accuracy: 70% → 94%.
Advanced Retrieval Pipeline — Azure Search reranking with DSPy-driven dynamic keyword generation and recursive retrieval. ~4-sec streaming response time.
Nov 2023 — Mar 2024
Lead Data Scientist
SNCF Connect & Tech
QA ChatBotLlamaIndexVespa.ai
QA ChatBot — LlamaIndex RAG + LangChain with auto-retriever composition on Vespa.ai, covering dozens of FAQ topics with sub-50ms retrieval latency.
Dec 2021 — Oct 2023
Lead Data Scientist
Wiley — Remote (International)
Hybrid Search8K+ Skills ModelDocker/K8sBedrock
Hybrid Search Engine — ANN + BM25 with spell correction, autocompletion, and multilingual search serving millions of learners; deployed via Docker & Kubernetes with 4 APIs.
Automated Skill-Tagging — Model covering 8,000+ skills at 95% precision, with full MLOps pipelines (SageMaker, MLFlow, Lambda, Step Functions).
Jun 2019 — Sep 2021
Lead Data Scientist
Orange Bank
KYCChurn PredictionAWS TextractLightGBM
KYC Remediation — AWS Textract for ID document analysis, MRZ consistency checks via checksum validation, and CRM consistency using text mining.
Churn Prediction — Predictive risk model on customer banking activity; optimized with HyperOpt and LightGBM for improved retention strategies.
Feb 2019 — May 2019
Senior Data Scientist
Carrefour
Cross-SellReco SystemPySparkGCP
Cross-Sell Reco Engine — Recommendation system integrating business rules, seasonality, and recurrence with personalized homepage allocation; PySpark/HDFS/Hive on GCP.
Oct 2017 — Nov 2018
Senior Quantitative Investment Strategist
Société Générale ATS
ERP StrategiesML PricingFACTSET
Equity Risk Premia — Developed and launched ERP strategies with ML algorithms (Random Forests, SVM), index pricing models, and full integration with trading systems and FACTSET API.
2008 — 2017
Quantitative Analyst & Data Scientist
Thomson-Reuters · RBC Dexia · PhD Researcher
OTC derivatives pricing (swaps, CDS, swaptions, TRS), front-office quant support (Kondor+), and PhD research on numerical methods for BSDEs, Lévy processes, and portfolio optimization via Malliavin calculus.

Education & Certifications

🎓
PhD Applied Mathematics
Cadi Ayyad University — 2016
🎓
Master MASEF
Paris-Dauphine — 2008
☁️
AWS ML Specialty
Certified — 2020
☁️
Azure AI Engineer
In Progress — 2026