Description

I design and ship prod grade GenAI systems. My focus is turning large language models into reliable, secure and useful tools embedded in real business workflows.

I currently work as a GenAI Engineer on a large-scale Loyalty Platform at Amadeus, where I build AI assistants used by product and support teams to search knowledge, execute actions and interact with complex systems through RAG, tool-calling and AI agents. Before that, I built and monitored RAG-based chatbots and agentic systems for enterprise clients at SaaSOffice, with strong emphasis on quality, traceability and observability.

What I help you with:

Building RAG pipelines on internal documentation (Confluence, SharePoint, PDFs, APIs, databases)
Designing AI assistants & copilots that actually execute tasks via tools and APIs
Creating secure, scalable GenAI backends (FastAPI, Java, Azure, Docker, Kubernetes)
Improving LLM reliability: evaluation, logging, hallucination control, prompt & retrieval tuning
Integrating AI into existing products and workflows

Tech stack:

LLMs & Orchestration: OpenAI, Azure AI Foundry, LangChain, agents, function calling
RAG & Search: vector databases, embeddings, document pipelines, chunking strategies
Backend & APIs: Python (FastAPI), Java (Spring), REST, tool APIs
Infra & Ops: Docker, Kubernetes, CI/CD, cloud deployments
Monitoring: Langfuse, custom evaluation, logging & feedback loops

Open to diverse AI missions:

My background includes:

Machine Learning & NLP (research projects at Inria, large-scale text classification, transformers, LSTM, fine-tuning)
Computer Vision (YOLO, image processing, detection and recognition pipelines)
Advanced research topics such as neuromorphic models and attention mechanisms, explored in academic and experimental settings

I’m also open to teaching, training and mentoring roles: helping teams, students or organizations understand and adopt modern AI, from fundamentals to production-grade systems.

Langues

Français
Bilingue ou natif
Anglais
Capacité professionnelle complète

Préférences en matière de lieu de travail

Accepte de travailler sur site

Paris (jusqu’à 50 km)

Amadeus
GenAI Developer
septembre 2025 - Aujourd'hui (9 mois)
Working on the development and deployment of AI Assistants within the Amadeus Loyalty Platform, where I design RAG, agents and tool-calling capabilities across the Azure ecosystem to support their integration into real product workflows.
intelligence artificielle Azure AI Gestion de projet agile Python Intégration d’une API externe
SAAS OFFICE
AI Engineer
mars 2025 - août 2025 (5 mois)
06560 Valbonne, France
Contributed to the development and optimization of intelligent chatbots using Retrieval-Augmented Generation (RAG) models. Focused on improving pipeline efficiency, monitoring agent performance, and implementing scalable AI solutions tailored for SaaS platforms and enterprise use cases.
intelligence artificielle Python Intégration d’une API externe Pipelines de données et entreposage Web Scraping
Inria
NLP & Machine Learning Engineer
juin 2024 - septembre 2024 (3 mois)
06560 Valbonne, France
Working with the WIMMICS team on the CIGAIA project, focusing on the collection and processing of textual data related to the Ukraine-Russia war.
Machine learning Deep Learning TensorFlow NLP Data science