Internship – Data Science (M/F) – Development of an Intelligent Chatbot for Regulatory Database Search

Founded in 2014, Sim&Cure is French digital start-up focused on improving neurovascular treatments of cerebral aneurysm with a proprietary software suite. The Sim&Size™ software is a Class II medical device with CE mark and FDA clearance that has already been used to treat more than 10,000+ patients in 500+ hospitals in the world.

Through several modules, Sim&Size™ is a software suite that provides to the physician a 3D visualization of medical images and a computational model of neurovascular implantable medical devices (IMDs). The therapeutic strategy is the most important step of this disease treatment and Sim&Size™ is now part of it by being efficient, safe, and reproducible. Computational modeling of specific devices in the anatomy of a patient helps the physician to achieve the intended outcome of the intervention.

Professionals in the medical and pharmaceutical industries must navigate vast and complex regulatory corpora (EU directives, ISO standards, FDA guidelines, etc.). Searching for precise information in these documents is time-consuming and inefficient.The goal of this internship is to design and develop an intelligent conversational system to facilitate regulatory information retrieval.

Main objectives

Develop a chatbot system capable of:

1. Indexing and structuring a database of regulatory texts.

2. Understanding users’ natural language queries.

3. Extracting and summarizing relevant information.

4. Providing contextual answers with precise references to sources.
   

• Advanced NLP: embeddings, semantic search, LLMs

• Data architecture: vector databases, indexing

• Full-stack development: REST API, user interface

• AI evaluation: relevance metrics, benchmarking
  

• Desired profile

  • Level: Master’s Degree (final year) / Engineering school

  • Strong skills in Python and software development

  • Knowledge in machine learning and NLP

  • Interest and experience in conversational AI

  • Prior experience with chatbot projects

  • Rigor, autonomy, and proactive attitude

  Duration: 4–6 months

  Technologies: Python, NLP, RAG, Vector Databases, LLM