Generative AI and large language models (LLMs), such as Copilot and ChatGPT can complete code based on initial fragments written by a developer. They are integrated in software development environments such as VS code. Many papers analyze the advantages and limitations of these approaches for code generation. Besides some deficiencies, the produced code is often correct, and the results are improving.

However, a surprisingly small amount of work has been done in the context of software modeling. The paper from Cámara et al. [1] concludes that while the performance of the current LLMs for software modeling is still limited (in contrast to code generation), we should adapt our model-based engineering practices to new assistants and integrate these into MBSE methods and tools.

The goal of this post-doc is to explore generative AI in the context of system modeling and associated tool support. For instance, AI assistance can support the completion, re-factoring, and analysis (for instance, identified design patterns or anti-patterns) at the model level. Propositions are discussed in the team and, in a second step, prototyped and evaluated in the context of the open-source UML modeler Papyrus.

[1] Javier Cámara et al. On the assessment of generative AI in modeling tasks: an experience report with ChatGPT and UML, Software and Systems Modeling (2023)

An ideal candidate has double competence. On the one hand, in generative AI, including, for instance, LLMs, prompt engineering, RAG. On the other hand in software engineering, notably based on model-driven approaches.

Applications should contain detailed experience, background information, and a recommendation letter.

In accordance with the commitments made by the CEA in favor of the integration of people with disabilities, this job is open to everyone. The CEA offers accommodations and/or organizational possibilities for the inclusion of disabled workers.