Master 2 Internship (H/F) - Runtime Monitors of Neural Network in Aerospace Applications

CNRS

Toulouse

On-site

EUR 5,700 - 7,700

Full time

46 hours ago
Be an early applicant

Get a reply from this employer

Your resume and cover letter, tailored to exactly what they’re hiring for.

Get past ATS filters

Job summary

LAAS-CNRS propose un stage Master 2 à Toulouse sur les Moniteurs d’exécution des réseaux de neurones en aérospatial. Le candidat travaillera sur des mécanismes de surveillance pour déceler des échecs de prédiction et développera un cadre de test autour du projet LARD/Lardon-x.

Le stage dure 5–6 mois, localisation Toulouse, rémunération d’environ 600 € par mois, supervision par Jérémie Guiochet et enrichissement en génération de données et évaluation de systèmes IA sensibles à la sécurité.

Qualifications

  • Étudiant en Master 2 (MSc) en informatique ou IA.
  • Stage de fin d’études dans le domaine IA et sécurité des systèmes.
  • Connaissances en apprentissage automatique et surveillance de réseaux de neurones.

Responsibilities

  • Explorer des stratégies de génération et de sélection de données pour l’évaluation des moniteurs.
  • Développer un cadre de test et d’évaluation d’un ou plusieurs mécanismes de surveillance proposés par la communauté IA.
  • Travailler sur le cadre LARD/Lardon-x en contexte aéronautique et runway detection.

Skills

Machine Learning
Safety Monitoring
Runtime Monitors

Education

Master 2 (MSc) in Computer Science or AI

Tools

Python
AI Frameworks

Job description

Complet

31031 TOULOUSE

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.

Transport

Référence de l’offre UPR8001-JERGUI-009

Get your free, confidential resume review.

or drag and drop your file here.

Similar jobs

Similar jobs worth comparing

Master 2 Internship: Aerospace AI Runtime Monitors
Master 2 Internship: Aerospace AI Runtime Monitors

CNRS • Toulouse

On-site
EUR 5,700 - 7,700
Master 2 Internship - Neurosymbolic Test Case Generation and Selection (H/F)
Master 2 Internship - Neurosymbolic Test Case Generation and Selection (H/F)

Cnrs Inc • Toulouse

On-site
EUR 5,700 - 7,700
Internship in AI: Graph-based Artificial Neural Networks H/F - Grenoble
Internship in AI: Graph-based Artificial Neural Networks H/F - Grenoble

CEA • Grenoble

On-site
EUR 11,000 - 13,000
Stage: Évaluation et intégration d’algorithmes de détection et suivi d’objets par deep learning (F/H)
Stage: Évaluation et intégration d’algorithmes de détection et suivi d’objets par deep learning (F/H)

HEMERIA • Angoulême

On-site
EUR 13,000 - 18,000
STAGE - IA générative & agentique pour les capteurs d'imagerie spatiale H/F
STAGE - IA générative & agentique pour les capteurs d'imagerie spatiale H/F

CNES • Toulouse

Hybrid
EUR 10,000 - 17,000
Stage rémunéré
Travail sur infrastructure GPU
Projets POC concrets
Internship - Data Scientist - Agentic ai & Deep Learning Rafa Project H/F
Internship - Data Scientist - Agentic ai & Deep Learning Rafa Project H/F

Cmacgm • Marseille

On-site
EUR 10,000 - 12,000
STAGE 2027 - AI Engineer (H/F)
STAGE 2027 - AI Engineer (H/F)

Aimlroles • Marseille

On-site
EUR 10,000 - 17,000
Internship - Implementation and validation of control algorithms for drones (M/F)
Internship - Implementation and validation of control algorithms for drones (M/F)

Inria • Villeneuve-d'Ascq

Remote
EUR 11,000 - 17,000
Partial reimbursement of public travel
Leave based on presence
Professional equipment available
Testia SAS - Stage - Segmentation par IA (H/F) - Rennes
Testia SAS - Stage - Segmentation par IA (H/F) - Rennes

Airbus SE • Rennes

On-site
EUR 8,900 - 13,000
Tickets restaurants
Participation transport
Gratification légale
Stage Human-Object Interaction benchmarking-Saclay-H/F
Stage Human-Object Interaction benchmarking-Saclay-H/F

CEA • Saclay

On-site
EUR 12,000 - 16,000