You're seeing this page as if you were . The main menu is still yours, though. Exit from immersion
Paul Moïse GangbadjaPM

Paul Moïse Gangbadja

ML Engineer| Generative AI Engineer

450 €/jour
Avignon, FR
3-7 ans

Délai de réponse moyen : 1h

À propos de Paul Moïse

Machine Learning & AI Engineer | NLP, LLMs, RAG, Azure | End-to-End AI Solutions

As an AI & Machine Learning Engineer with hands-on experience deploying scalable GenAI solutions in the enterprise, I specialize in building NLP applications, Retrieval-Augmented Generation (RAG) systems, and LLM-driven chatbots that deliver real business value.

🔹 At Amadeus, a global leader in travel tech, I designed and deployed a company-wide AI chatbot using Azure OpenAI and RAG architecture. I migrated it to Agentic RAG using Langgraph. I tackled challenges like document ingestion, vector database optimization, prompt tuning, and compliance with the AI Act—all while driving adoption across departments.

🔹 I hold a Master's degree in AI from CERI Avignon, with a strong academic and practical foundation in transformers, deep learning, and MLOps (MLflow, Optuna, LighGBM, XGBoost, Scikit-learn).

🔹 Whether you need:

- Custom LLM fine-tuning or evaluation
- Intelligent document search with vector databases
- AI assistants that understand your business context
- Data pipelines, dashboards, or ML experimentation tools

I can help you move from idea to deployment.

✅ Strong coding and deployment skills (Python, PyTorch, Scikit-learn, Azure, Streamlit)
✅ Fluent in both English and French
✅ Reliable, collaborative, and always learning

Let’s build something impactful with AI. I’m available for both short-term help and long-term collaboration.
  • Français

    Bilingue ou natif

  • Anglais

    Capacité professionnelle complète

En télétravail uniquement
Travaille majoritairement à distance

Expériences

  • AMADEUS
    Generative AI Engineer
    TRANSPORTS
    septembre 2023 - juillet 2025 (1 an et 10 mois)
    Nice, France
    Developed and scaled an LLM-powered internal chatbot for enterprise knowledge access using RAG for contextual, accurate answers. Migrated to an Agentic RAG architecture with LangGraph, enabling modular reasoning and multi-step workflows. Built a FastAPI async backend and a modern React frontend. Integrated Langfuse for observability (cost, latency, prompt versioning) and DeepEval for output evaluation. Used Azure AI Search as the vector database. Designed a PostgreSQL-based trace system to persist agent state and conversation history. Integrated Azure OpenAI (GPT-4.0/4.1) for generation. Deployed the full-stack app to Azure Web App. Ensured compliance with AI governance (AI Act) and drove adoption across departments by iterating on feedback and improving UX.

    Key Tools: FastAPI, React, Azure OpenAI, LangGraph, LangChain, Langfuse, DeepEval, Azure AI Search, PostgreSQL, Streamlit, MLflow, Transformers, RAG, NLP
    FastAPI Azure OpenAI LLM Langchain React.js
  • Erugis
    Developer FullStack
    RESSOURCES HUMAINES
    février 2022 - août 2023 (1 an et 6 mois)
    Nice, France
    - Contributed to the development of Uptimise, an HR management platform tailored for the African market.
    - Designed and implemented three key microservices: Paid Leave, File Storage, and Expense Management.
    - Built secure, scalable backend APIs using Django REST Framework, with Django Tenant to support multi-tenancy.
    - Developed responsive frontend components with React and TypeScript, ensuring seamless integration with backend services.
    - Managed relational data with PostgreSQL (schema-based separation per tenant) and integrated Keycloak for authentication and identity management.
    - Enabled asynchronous communication between services using Kafka, improving performance and decoupling service dependencies.
    - Containerized services with Docker for reproducible environments and easier deployment.

    Tech Stack: Django REST, Django Tenant, PostgreSQL, React, TypeScript, Kafka, Docker, Keycloak, Git
    Management CI/CD Python Django Rest Framework React.js Docker

Recommandations

Soyez le premier à recommander Paul Moïse

Contribuez à la réussite de ce freelance en partageant votre expérience de collaboration avec lui.

Ces profils de freelance correspondent également à vos critères

AgathaA

Agatha Frydrych

Backend Java Software Engineer

4.7

(3)

2

BaptisteB

Baptiste Duhen

Fullstack developer

4.6

(4)

5

AmedA

Amed Hamou

Senior Lead Developer

4

(2)

7

AudreyA

Audrey Champion

Web developer

4.3

(3)

4

Formations

  • Master in Intelligence Artificielle
    Avignon University (CERI)
    2025
    Machine learning, Deep Learning, Software Engineering
  • Bachelor's degree in Artificielle Intelligence
    Côte d'Azure University
    2023

Compétences

Catégories