Internship Offer: Multi-Modal Retrieval-Augmented Generation (RAG) (H/F)

Internship Offer: Multi-Modal Retrieval-Augmented Generation (RAG) applied on Compliance / Financial Security topics

We are pleased to announce an exciting internship opportunity within our team. The focus of this internship is on Multi-Modal Retrieval-Augmented Generation (RAG). You will be a part of AI project in the Compliance department at BGL BNP Paribas and work in close cooperation with the data science Laboratory.

Internship Overview

In the context of the continuous improvement of compliance processes and tools, the goal of this internship is to participate in a compliance project - Financial Security related - involving multimodal retrieval of data and information extraction tailored to specific business needs. A background in Retrieval-Augmented Generation (RAG), computer vision, and Natural Language Processing (NLP) is considered a plus.

Key Responsibilities

• Implementing and enhancing methods for multimodal data retrieval, reranker and information extraction.
• Conducting comprehensive evaluations of models to ensure their accuracy and reliability.
• Designing and refining deep learning architectures to improve performance and efficiency.
• Training models to achieve robust and generalizable results across various business-related applications.
  
  

You will be a part of Compliance Function and work in close cooperation with the Data Science Laboratory at BGL BNP Paribas.

Qualifications

To be considered for this internship, candidates should possess the following:

• Strong knowledge in model evaluation techniques, including metrics and benchmarks.
• Experience in training and tuning deep learning models.
• Interest in embeddings and multimodal large language models (LLMs) with a scientific approach.
• Background in OCR, vision models, or NLP is advantageous.
• Ability to work both independently and collaboratively within a team.
• Excellent problem-solving skills and attention to detail.
• Good skills in Python coding for fast experimenting of ideas.
• Ability to make the bridge between technical topics and business requirements
  
  

Education

Master of Science in Engineering

Engineering School