L'offre PhD – Verifiability of systems hosting software developed from machine learning - 10447759 (m/f). a été sauvegardée.


Offre sauvegardée

Entrez votre adresse e-mail pour enregistrer ce travail

Vous enregistrez ce travail sous:

retour à la liste

PhD – Verifiability of systems hosting software developed from machine learning - 10447759 (m/f). posté par AIRBUS

CDD/Intérim - temps plein

Description de l'offre

Airbus Operations SAS

Airbus is a global leader in aeronautics, space and related services. In 2018 it generated revenues of € 64 billion and employed a workforce of around 134,000. Airbus offers the most comprehensive range of passenger airliners. Airbus is also a European leader providing tanker, combat, transport and mission aircraft, as well as one of the world's leading space companies. In helicopters, Airbus provides the most efficient civil and military rotorcraft solutions worldwide.

Our people work with passion and determination to make the world a more connected, safer and smarter place. Taking pride in our work, we draw on each other's expertise and experience to achieve excellence. Our diversity and teamwork culture propel us to accomplish the extraordinary - on the ground, in the sky and in space.

Description of the job

We offer the opportunity to work in an environment where basic research and industrial needs combine naturally.

The research is done in the framework of a collaboration between IRIT (Institut de Recherche en Informatique de Toulouse – Toulouse Institute of Computer Science Research) and Airbus. Toulouse is ranked 1st in the top 10 best student cities in France (L’Etudiant 2019) and is the 2nd town in France by number of students (115000 students, 10000 researchers). Toulouse also hosts major companies that develop embedded software and large software systems.

The thesis will take place in the Systems General Domain of AIRBUS on St Martin site (M01 Building) and specifically in the EYDZW group.
EYDZW is a transnational group gathering a high level of experience in HW and SW development in front of aeronautics standards. We assure through audits that Software comply with certification requirements, Airbus safety and functional requirements.

We are anticipating future regulation for new technologies and prepare them with Industry and Airworthiness Authorities

Tasks & accountabilities

This research aims at investigating how to include machine learning techniques into the software development lifecycle, while keeping safety and security standards at their highest level.

The PhD candidate will contribute to extending the existing skills on development of systems based on ML algorithms at Airbus and to the future rule making with certification authorities (EASA).

The main objective of the thesis is to develop a new design assurance methodology ensuring the conformity to existing and future regulation objectives. Basic research into verification and validation of machine learning-based software is necessary and will drive the definition of the assurance methodology.

1-Statement of concerns: identify the gap between the current programmed software technics and the ML based software development methodology and consequently the lack in the current design assurance used for certification purposes
2-Solution proposal: Define a new methodology of design assurance to guarantee that the development of a ML-based SW will meet the industrial and regulation requirements.

3-Apply the new methodology on a use case and make recommendations for Authorities future rulemaking

This job requires an awareness of any potential compliance risks and a commitment to act with integrity, as the foundation for the Company’s success, reputation and sustainable growth.

Required skills

We are looking for a motivated candidate with a strong background in one or more of the following skills, having a hands-on experience on software development or an affirmed interest in:

- Langages & Programmation : C, C++, C#, JAVA, Python

- System engineering

- (formal) Validation and verification

- Big Data, Data Science, Mathématiques, Statistiques

- Machine learning, Deep learning, AI, Visualisation

Numéro de référence

10447759 SC EN EXT 1

Offres similaires

Recevoir des offres similaires

Merci. Vous allez recevoir des offres à l'adresse email