Get a reply from this employer
Your resume and cover letter, tailored to exactly what they’re hiring for.
CNRS - LAAS-CNRS, Toulouse, propose un stage Master 2 axé sur les Runtime Monitors des réseaux neuronaux dans des applications aéronautiques. Le stage est en environnement CNRS et se déroule à Toulouse, avec une mission axée sur les données et la surveillance de systèmes d’IA.
Vous travaillerez sur la génération et la sélection de données, et sur le cadre de tests des moniteurs dans un contexte aéronautique, avec une collaboration étroite avec l'équipe LAAS-CNRS.
Nouveau
TOULOUSE
Cette offre est ouverte aux personnes disposant d’un titre leur reconnaissant la qualité de travailleur handicapé ou travailleuse handicapée.
Laboratoire d'analyse et d'architecture des systèmes
Convention de stage
Complet
31031 TOULOUSE
5 mois
01/02/2027
Title: Master 2 Internship - Runtime Monitors of Neural Network in Aerospace
Supervisors: Jérémie Guiochet (https://homepages.laas.fr/guiochet)
Profile: Computer Science, AI
Level: Master 2 (MSc)
Duration: 5–6 months
Location: LAAS-CNRS, Toulouse, France (https://www.laas.fr)
Salary: ~€600/month
Keywords: Computer Science, Artificial Intelligence, Machine Learning, Data Generation, Safety Monitoring
Technologies: Python, AI Frameworks
Artificial intelligence (AI) is increasingly being used in safety-critical applications, such as autonomous vehicles and surgical robotics. In these systems, perception tasks largely rely on deep neural networks (DNNs). However, the use of these components remains challenging because their behavior cannot be fully guaranteed, raising concerns about reliability and safety. Runtime monitoring mechanisms are among the promising approaches to address these limitations. Their purpose is to continuously monitor neural network behavior in order to detect or prevent potential errors. Two main families of monitors can be distinguished: rule-based monitors, which verify whether predefined safety properties are satisfied, and data-driven monitors, which are themselves developed through machine learning, often using neural networks.
Evaluating the performance of these monitors is essential, particularly in situations where the main neural network produces incorrect predictions. This raises several important questions: What data should be used to evaluate these monitors? How should such data be collected, generated, and selected? How can the dataset cover both nominal and abnormal operating conditions?
The objective of this internship is to investigate data generation and selection strategies for monitor evaluation and to develop a framework for testing and evaluating one or more monitoring mechanisms proposed by the AI research community. The internship will be conducted as part of an aviation-related case study, focusing on runway detection during aircraft landing approaches. It builds on the LARD (Landing Approach for Runway Detection) tool and dataset, which we have extended into Lardon-x, a tool currently under development at ANITI and LAAS-CNRS.
www.laas.fr
Référence de l’offre UPR8001-JERGUI-009 Secteur d’activité Sciences du vivant, de la terre et de l'environnement
Le CNRS est un acteur majeur de la recherche fondamentale à une échelle mondiale. Le CNRS est le seul organisme français actif dans tous les domaines scientifiques. Sa position unique de multi-spécialiste lui permet d’associer les différentes disciplines pour affronter les défis les plus importants du monde contemporain, en lien avec les acteurs du changement.
Les métiers de la recherche