Specializing in Document Intelligence and Large Language Models. I build end-to-end AI solutions for complex document processing, RAG systems, and information retrieval at scale.
I am a Data Scientist at SocGen AI, focused on accelerating AI integration to automate and optimize banking processes. My work emphasizes responsible AI deployment, regulatory compliance (EU AI Act), and building innovative solutions with a strong focus on operational efficiency.
My core expertise involves:
- Document AI: Multimodal transformers and layout analysis.
- Information Retrieval: Enterprise-grade indexing systems and vector search.
- Generative AI: LLM reasoning, Chain of Thought approaches, and RAG architectures.
Languages
- Python, SQL
NLP & LLMs
- RAG Architectures, LLMOps
- Prompt Engineering, Fine-tuning (PEFT, LoRA), RLHF
- Frameworks: LangChain, LlamaIndex
Machine Learning & Frameworks
- PyTorch, TensorFlow, Scikit-learn
- Computer Vision: Document Layout Analysis, OCR, Vision Transformers (ViT), YOLO
Data Infrastructure & MLOps
- Vector Databases: Qdrant, Vespa, FAISS, PostgreSQL
- Cloud & Operations: AWS, Azure AI Studio, Docker, Git
- Experimenting with reasoning models and advanced inference strategies.
- Improving efficiency in document indexing and retrieval systems.
- Exploring multimodal architectures for enhanced document understanding.