I am a motivated data scientist and AI engineer with a strong academic background in data science, artificial intelligence, and deep learning from prestigious institutions such as Université Paris 1 Panthéon-Sorbonne and École Polytechnique. I am passionate about leveraging large language models and AI techniques to build innovative systems tuned to various business contexts. Throughout my career, I have worked on projects involving natural language processing, knowledge management, chatbot development, and predictive analytics using a wide array of tools and frameworks including PyTorch, TensorFlow, HuggingFace, FastAPI, AWS SageMaker, and PySpark. I enjoy solving complex problems and delivering effective AI solutions with a collaborative and professional approach.

Bouthaina Cheboutia

I am a motivated data scientist and AI engineer with a strong academic background in data science, artificial intelligence, and deep learning from prestigious institutions such as Université Paris 1 Panthéon-Sorbonne and École Polytechnique. I am passionate about leveraging large language models and AI techniques to build innovative systems tuned to various business contexts. Throughout my career, I have worked on projects involving natural language processing, knowledge management, chatbot development, and predictive analytics using a wide array of tools and frameworks including PyTorch, TensorFlow, HuggingFace, FastAPI, AWS SageMaker, and PySpark. I enjoy solving complex problems and delivering effective AI solutions with a collaborative and professional approach.

Available to hire

I am a motivated data scientist and AI engineer with a strong academic background in data science, artificial intelligence, and deep learning from prestigious institutions such as Université Paris 1 Panthéon-Sorbonne and École Polytechnique. I am passionate about leveraging large language models and AI techniques to build innovative systems tuned to various business contexts.

Throughout my career, I have worked on projects involving natural language processing, knowledge management, chatbot development, and predictive analytics using a wide array of tools and frameworks including PyTorch, TensorFlow, HuggingFace, FastAPI, AWS SageMaker, and PySpark. I enjoy solving complex problems and delivering effective AI solutions with a collaborative and professional approach.

See more

Experience Level

Expert
Expert
Expert
Expert
Expert
Intermediate
Intermediate
Intermediate
Intermediate
See more

Language

French
Advanced
English
Advanced

Work Experience

NLP Data Scientist at Renault
September 1, 2025 - August 7, 2025
Worked on contextualization of large language models (LLMs) integrating business knowledge. Explored advanced graph-based methods for knowledge extraction and comparison of research models (SBERT, TF-IDF, ColBERT) with evaluations. Developed a unified API combining all tested approaches to facilitate application deployment.
Consultante Gen AI Freelance at Voxist
March 1, 2025 - August 7, 2025
Developed knowledge management systems generating knowledge graphs, extracting entities, and creating ontologies from documents using large language models and prompt engineering. Optimized system response times using async IO and implemented graph-based knowledge systems on OnTotext. Processed medical transcriptions by automating correction, report generation with LLMs, and classification to simplify workflows.
Consultante stagiaire Data Scientist at Voxist
September 1, 2024 - August 7, 2025
Designed and deployed an intelligent chatbot based on Retrieval Augmented Generation (RAG) and various LLMs (GPT, llama, mixtral) for the Infodis group. Fine-tuned embedding models (OpenAI, BERT) to improve performance. Integrated a multi-agent system including implementations with OpenAI, LlamaIndex, LangChain, and Langfuse. Developed and deployed client solutions using FastAPI. Created chatbot solutions for hotel client support based on RAG and LLM models.
Data Engineer at Ooredoo
April 1, 2022 - August 7, 2025
Extracted, cleaned, and processed client data using Excel and SQL queries. Conducted exploratory analysis of purchase behavior and customer segmentation (PCA, K-Means, GMM) to identify profile types. Modeled business intelligence solutions with star schema design, ETL pipeline development (SQL), and OLAP analysis. Created interactive dashboards in Power BI for revenue and cost monitoring.

Education

Master 2 Traitement de l'Information et Data-Science en Entreprise at Université Paris 1 Panthéon-Sorbonne
September 1, 2024 - November 1, 2025
Ingénieur d'état en Data science et Intelligence Artificielle at École Polytechnique
September 1, 2019 - July 1, 2024

Qualifications

Add your qualifications or awards here.

Industry Experience

Software & Internet, Professional Services, Financial Services, Manufacturing, Travel & Hospitality