The LSEA (Embedded and Autonomous Systems Design Laboratory) is offering an post-doctoral position for a highly motivated person to work in the areas of Safety and Assurance of AI systems.*Working context*The LSEA is part of CEA, one of the best-ranked research institutions in the world[1]. The lab has a recognized expertise in the field of model-based design of safety-critical systems. It has initiated an upstream work for the mastery of advanced technologies of safe self-adaptation and integration of trustworthy autonomy in critical systems. Lab members are strongly involved in various industrial projects as well as collaborative French and European research projects.
*Your mission*The position is related to safety assessment and assurance of AI systems that used machine-learning components during operation time for performing autonomy functions. Currently, for non-AI system, the safety is assessed prior to the system deployment and the safety assessment results are compiled into a safety case that remains valid through system life. For novel systems integrating AI components, particularly the self-learners systems, such engineering and assurance approach are not applicable as the system can exhibit new behavior in front of unknown situations during operation.
The goal of the postdoc will be to define an engineering approach to perform accurate safety assessment of AI systems. A second objective is to define assurance case artefacts (claims, evidences, etc.) to obtain & preserve justified confidence in the safety of the system through its lifetime, particularly for AI systems with operational learning. As a detailed work plan, the postdoc will :
· study state of the art and practice of existing standards, processes, methods, tools for ensuring functional safety of AI systems
· define an engineering approach to handle the safety of AI-based systems at design and operational time.
· define a safety case strategy that supports the engineering approach to justify from the system safety at design and operational time
· implement the approaches in a framework and evaluate them on some applications
The position holder will join a research and development team in a highly stimulating environment with unique opportunities to develop a strong technical and research portfolio. He will be required to collaborate with LSEA academic & industry partners, to contribute and manage national & EU projects, to prepare and submit scientific material for publication, to provide guidance to PhD students.
* Qualifications and recruiting conditions*Successful candidates must hold a PhD (or be near completion) in software engineering, computer science or a closely related topic. We are mainly looking for applicants with excellent research records in safety and system engineering, software/system modelling, and with strong programming skills (Java, python). Excellent programming skills are highly desirable. Background on AI algorithms foundations and system assurance and certification will be considered an advantage. Practical experience with Eclipse IDE and languages (e.g., UML and
https://eclipse.org/modeling/) is a plus.
Application must be sent to Chokri Mraidha (
Chokri.Mraidha@cea.fr), morayo.adedjouma (
morayo.adedjouma@cea.fr) and should include:
o Curriculum Vitae including background information, detailed work experience, list of publications
o Motivation letter
o contact information for 2 referees
Early submission is encouraged; applications will be processed upon arrival.*Remuneration package*Remuneration for the position includes a gross annual salary ranging from 33k EUR to 39k EUR (the level of appointment will be commensurate with experience of the candidate), full access to the French healthcare, social care and pension system, as well as several other benefits like coverage of 50% of all your public transport fees.
*Working and living in paris*Our offices are located in Plateau de Saclay, south of Paris, the French biggest research and industry cluster. Our welcome agency “Sciences Accueil” is available to help you find your home and settle here.
