Main
Phileas CONDEMINE
In short
2025–Present Principal Data Scientist P&C @ SCOR: Developing P&C use cases for AI Assistant, a GenAI-powered document extraction product; mentoring six P&C data scientists and collaborating with the product’s 20 contributors, as well as the technical and business teams building and using tools powered by AI Assistant.
2021-2025 Lead ML-Engineer NLP @ COVEA : Delivering Hybrid AI and Gen-AI Efficient and Frugal Solutions in Production with Azure, OpenAI & Databricks.
2018-2021 Senior Data Scientist @ Ministère de la Santé : Modelling Health Sequences with Transformers. Help Data-driven decision-making during CoViD-19 crisis.
2014-2017 Actuarial Data Scientist @ AXA Global P&C : pricing and claims handling with machine learning and external data.
Experience
Principal Data Scientist P&C
SCOR
Paris, France
2025–Present
Developing P&C use cases for AIssistant, a document extraction product with around 20 contributors.
- Provide technical leadership for six P&C data scientists through mentoring, merge request reviews, shared development practices and code reuse.
- Collaborate with contributors across the product on shared features, including the migration from GPT-4.1 to GPT-5.4 and evaluation and observability tools. Work with the technical and business teams building and using applications powered by AIssistant.
- Build an automated feedback loop: collect business users’ validations, evaluate extraction quality, improve prompts and post-processing, and validate changes.
- Improve the reliability of LLM outputs through structured outputs validated with Pydantic; develop trace analysis and performance monitoring to support debugging.
Lead ML-Engineer NLP
COVEA - AI Delivery
Paris, France
2021-2025
- VOX.IA : Client Verbatim Analysis. AI Award-Winning Project.
- NetMessages : Offer real-time selfcare offer to the client with Frugal AI.
- JudiCible : Accelerate Claim Management with AI & Gen-AI Hybrid approach.
- AI in Production : Annotation, Finetuning, Deployment, Drift-Monitoring.
- Publication on Medium COV&IA.
Senior Data Scientist & (EIG)
Ministry of Health
Paris, France
2018-2021
- Modelling Health Sequences to predict diseases outcome and detect disruption.
- Classification with active-learning & General Public WebApp to find Health-focused statistics.
- Tools for regional health agencies : Interactive Decision Making Tool to help experts elaborate Zoning for health professionals.
- Tech Lead at CoViD-19 crisis center : Develop webapps to gather critical information from hospitals and labs.
- Workflow to build CoViD-19 Indicators with SIDep, SIVic, VacSI.
- Produce open-data with anonymisation : k-anonymity & hierarchical l-diversity.
Actuarial Data Scientist
AXA Global P&C
Paris, France
2014-2017
- P&C pricing innovation with gradient boosting and ML-interpretation / XAI techniques.
- Build and deploy Claim Cost Analyzer : ML workflow to score car repairers cost-efficiency.
- NLP on bodily injury cases to assess contentious risk.
- Roads own-risk assessement based on GPS Telematics data.
Structuration Intern
Exane BNP Paribas (6 months)
Paris, France
2013
Building a synthetic index as a dynamic basket of stocks & bonds.
CAT-Bonds Pricing Intern
SCOR (6 months)
Paris, France
2012
Pricing CAT-Bonds using Monte-Carlo Markov Chains MCMC.
Training
Deep learning
Advanced training & hands-on projects.
fast.ai, datascientest, deeplearning.ai
2017-2020
Spark & Scala
Scala Programming + Spark applications.
Coursera by Martin Odersky & Heather Miller
2019
Web Development
Introduction to HTML, CSS, Javascript & JQuery.
CodeSchool.com
2016
Introduction to data science
Main techniques of supervised & unsupervised learning : SVM, Gradient-Boosting, Random Forests, k-means etc.
Coursera by Bill Howe
2014
ENSAE Paris - IP Paris
MSc Actuarial Science & Data Science
Paris, France
2010-2014
Teaching
Gen-AI Masterclass (COVEA)
Gen-AI theory and practice. Applications with Copilot. Scaling with Azure OpenAI. Prompt-engineering.
COVEA
2023-2025
Data Science Teacher
Data-Science for Actuaries & 
Data Science Certification
Paris, France
2014-2020
- Natural Language Processing & Text-mining techniques.
- Machine Learning for structured data : Gradient Boosting & Support Vector Machine.
- Data Science Hands-On with R, data.table, xgboost, glmnet & liblinear…
- Build Interactive Apps with R + Shiny.
- Data Science for Actuaries (DS4A): 5-days training with hands-on & 1-day hackathon to teach AXA actuaries Data-Science Techniques that can help them better solve Insurance-related problems. The Theoretical Training was given by Arthur Charpentier.