Yasmine Ouyahya
Lead Data Scientist @VINCI Energies
Signup · Get unlimited contacts
WORK HISTORY
Lead Data Scientist @VINCI Energies
Exploring and improving Retrieval-Augmented Generation architectures with an emphasis on retrieval efficiency, context relevance, and factual grounding. Work involves custom parser development, retrieval pipeline optimization, and evaluation of hybrid retriever–generator systems for domain-specific applications.
EDUCATION
Université Paris-Saclay
Master 1 (M1) , Applied Mathematics
CPGE Lycée Pothier
classes préparatoires aux grandes écoles, Physique, sciences de l'ingénieur
ensIIE
Engineer's degree, Applied mathematics and computer science
University of Paris I: Panthéon-Sorbonne
Master of Science - MS, Modélisations statistiques économiques et financières (MoSEF) - Data Science
ABOUT YASMINE OUYAHYA
I am a Senior Data Scientist and Lead AI Engineer passionate about Generative AI, Large Language Models (LLMs), Machine Learning, and Deep Learning. My work spans the entire AI lifecycle, from research and model development to large-scale deployment and production optimization in enterprise environments. I currently specialize in Retrieval-Augmented Generation (RAG) and LLM-based systems, building reliable and scalable pipelines for hybrid retrieval (dense + sparse), custom retrievers, document parsers, reranking, context compression, and knowledge integration. I design and experiment with advanced RAG architectures, including agentic RAG, GraphRAG, and multimodal pipelines, as well as AI agents using frameworks like LangGraph and ReAct, that make LLMs more accurate, grounded, and adaptable to complex domain-specific tasks. My background in applied mathematics, software engineering, and cloud infrastructure (Azure certified) helps me bridge research innovation with production-grade implementation across large-scale organizations. Main areas of interest: Generative AI, LLMs, RAG systems, Agentic AI, Custom Retrievers & Parsers, Hybrid Retrieval, LLM Fine-Tuning, MLOps, NLP, Computer Vision, Multimodal AI, Time Series Forecasting, and ML Industrialization & Deployment.
This profile is compiled from publicly available professional sources. Unifers is not affiliated with or endorsed by LinkedIn. Request removal of this profile.