Freelancer profile translated to English.
Back to original languageAbout Djoupe Pene
I am now offering my services in data science, both from a project management and operational perspective, with a result-oriented approach. I can therefore intervene at different stages, from defining the need to delivering the final product, whether it be dashboards or ML models.
The world of data is evolving at lightning speed. To stay at the forefront, I continue to train myself in parallel with my freelance work. So, whatever your sector and the constraints of your request, I would be delighted to dive into a new universe. I adapt quickly to new technologies and work environments.
Contact me to learn more!
Techniques:
🔹 Modeling & Machine Learning: Development and optimization of Deep Learning models (CNN, Transformers, LLMs).
🔹 Data Processing: Preparation, cleaning, and structuring of datasets to ensure model quality.
🔹 Computer Vision: Detection, classification, and segmentation of images with advanced architectures.
🔹 Deployment & MLOps: Integration of models into production via API, Docker, and CI/CD.
🔹 Big Data & Cloud: Experience with cloud environments (AWS, Azure) and distributed frameworks.
🔹 Analysis & Visualization: Interactive dashboards and model interpretability for better decision-making.
French
Native or bilingual
English
Fluent
Can work on-site
Paris (up to 50km), Bordeaux (up to 10km), Toulouse (up to 10km)
Experience
- BpifranceData ScientistPUBLIC SECTORApril 2025 - May 2025 (1 month)Development of a Financial Strategy Improvement Chatbot• Collection and structuring of data from various sources for dataset preparation.• Selection and fine-tuning of Llama models to meet specific client needs.• Backend Development: Integration of AI models into a secure and scalable architecture.• Optimization of CPU and memory resources to ensure optimal performance.• Securing sensitive data and secure integration into a Docker environment.• Deployment of the system in production on an ultra-secure VPS.
- CapgeminiData ScientistOctober 2022 - October 2024 (2 years and 1 month)Paris, FranceEmotion, Gender, and Age Detection on an Embedded System• Complete project management, from design to integration of AI models on the target.• Development of a real-time facial recognition solution on an embedded system for simultaneous analysis of emotions, gender, and age with approximately 85% accuracy using AI models.• Efficient integration of detection algorithms on a POC (Raspberry Pi) to meet the resource constraints of an embedded system.Machine Learning with Python for Predictions• Supervised Learning: Supervised learning techniques (linear regression, decision trees, SVM, neural networks).• Unsupervised Learning: Use of clustering algorithms (K-means) and principal component analysis (PCA).• Data Preprocessing: Implementation of an ETL platform (Data cleaning, transformation, and normalization, handling missing values and outliers).• Model performance evaluation.Development of a Prediction Assistance Model for Diseases in Hospitals• Conducted a benchmark of existing data and solutions to align methods with project needs.• Collection and implementation of an ETL pipeline for processing over 10,000 radiographic images, improving their quality using Azure Data Factory, Azure Synapse Analytics, Azure Data Lake Gen 2, Databricks, Azure Key Vault.• Data visualization and rebalancing for analysis to optimize model training.• Development of a high-performance AI model (87% accuracy) integrated into a web application for doctors, with a CI/CD pipeline for fast and reliable deployments (Docker, Git, AWS) to ensure quick and continuous updates.
- VerdonData Scientist EngineerDecember 2024 - February 2025 (2 months)Paris, FranceDevelopment of a Personalized Chatbot• Analysis, processing, and cleaning of the company's unstructured database for better information exploitation.• Design and implementation of structured and optimized SQL databases for data storage and management in vectors.• Deployment of an optimized RAG solution for retrieving and generating information based on company data.• Structuring and indexing of data to improve vector search and reduce latency.• Development of a custom chatbot with advanced LLM models (Llama, DeepSeek).• Optimization of responses via vector databases (FAISS, ChromaDB, Pinecone) and hybrid engines.• Management of LLM challenges: hallucinations, response evaluation, context management.• Deployment of the chatbot and integration with existing systems.
Recommendations
These freelancer profiles also match your criteria
Agatha Frydrych
Backend Java Software Engineer
4.7
(3)
2
Baptiste Duhen
Fullstack developer
4.6
(4)
5
Amed Hamou
Senior Lead Developer
4
(2)
7
Audrey Champion
Web developer
4.3
(3)
4
Education
- Engineering Degree in Data and Artificial IntelligenceEcole Supérieur d'ingénieurs de Léonard de Vinci2024Mathematics, Machine Learning, Data analysis with Python, Big Data, Data visualization, WebScrapping, Data processing, Statistics, Computer Vision.