Freelancer profile translated to English.

Description

Engineer and PhD graduate from the University of Rennes 1 (Data Science, Statistics and Learning), I carry out your AI projects from A to Z, up to production deployment.

You are looking for an expert in generative AI, python, AI agent, LLM?

🎯 You are in the right place.

I am a Data Scientist with over 5 years of experience.

I have worked in various sectors such as industry, pharmaceuticals, medicine, automotive, scientific research...

Typical Projects

- Conversational AI Solution (chatbot, virtual assistant with RAG and LLM)

- Computer Vision System (images & videos)

- AI-driven Business Process Automation (automatic extraction, structured generation)

- Creation of Business Intelligence Dashboards with Power BI for business data visualization

Technical Skills

- AI & Machine Learning: PyTorch, TensorFlow, Scikit-learn

- Application Development: Python

- Business Intelligence & DataViz: Power BI (data modeling, DAX, creation of dynamic and interactive reports)

💡I can assist you with:

Creation and integration of conversational AI agents and LLMs

Customization of models like GPT or Llama

Data collection, cleaning, and preprocessing

Development and implementation of machine learning models and predictive algorithms

Exploration and comparison of models for appropriate technological choices

Python development of model training pipelines

Proposal of metrics to evaluate and monitor the performance of deployed models

Design of your AI solution architecture

Creation of Power BI reports for the analysis of your business data and monitoring of strategic KPIs

🧠Technical Skills:

LLM

RAG

Deep Learning

Image Processing

Computer Vision

Power BI / DAX / Data Modeling

Shall we discuss your project?

Contact me directly via the platform.

Looking forward to collaborating with you!

Industry field of expertise

Languages

French
Native or bilingual
English
Fluent

Workplace preferences

Can work on-site

Lyon (up to 50km)

ICBMS-3d.FAB
Data Scientist
November 2021 - August 2024 (2 years and 9 months)
Lyon, France
Data engineer in data, 3D object, and image processing
• Automation of 3D bioprinting, prediction of 3D object orientation (.STL) and 3D printing parameters.
• Integration of a corrective command system to improve 3D printing quality and reduce defects.
• Segmentation, detection, and tracking of cells from microscopic images to analyze cell deformability using supervised and unsupervised learning models (Unet, GAN, VAE)
• Use of supervised and unsupervised models and physical laws in latent space to predict bio-printability and cell viability.
Technologies: Python, OpenCV, Scikit-Learn, Pandas, Pytorch, Tensorflow,
Nvidia, high-speed camera, microfluidics, ISO13485.
Creation of an AI-based solution in the pharmaceutical field allowing users (healthcare professionals, researchers, pharmacists) to easily query pharmaceutical documents (leaflets, studies, PDF reports, etc.) via a natural language chatbot.

Main functionalities:
. Automatic document ingestion
. PDF document upload (drug leaflets, clinical trials, regulations).
. Intelligent data extraction with OCR + NLP.
. Structuring and indexing in a vector database.
. Automatic structuring into a database
. Semantic mapping to a predefined pharmaceutical database schema (drugs, active ingredients, dosages, side effects, interactions).
. Use of LLM models specialized in biomedical to extract relevant information.
. Results in the form of tables, lists, graphs.
. Visualization of results with Power BI: creation of interactive dashboards for analyzing extracted data (dosages, side effects, interactions, etc.)
. Export options (CSV, JSON, or interactive display).
PowerBI Pytorch Scikit-learn Dash Python
Laboratoire LIST– Sud-Est de Nankin
Image Processing & Computer Vision Engineer
June 2019 - September 2019 (3 months)
China
• Classification of elderly people's postures from thermal and depth images based on Deep Learning methods (SSD, YOLOv3, Faster R-CNN). Technologies: Python, Scikit-Learn, Tensorflow, Keras, Linux.
Python Developer Scikit-learn Deep Learning Python 3 keras
NeotecVision
AI and Computer Vision Engineer
January 2017 - January 2021 (4 years)
Rennes, France
• Tracking of elderly people in the context of fall detection using Bayesian models.
• Identification and classification of elderly people's postures in the context of fall prevention based on Deep Learning models (Faster R-CNN).
• Fusion of data from two different types of sensors that preserve anonymity: thermal and depth.
Technologies: Python, Matlab, OpenCV, Pytorch, Scikit-Learn, Tensorflow,
Nvidia, Kinect, Flir Lepton.
Matlab Pytorch TensorFlow OpenCV Nvidia