Description
Imagine a business process modeling assistant that goes beyond a standard GPT: guided, interactive, and aware of design constraints. In this thesis, you'll explore how AI and LLMs can support business analysts in designing advanced BPMN and DMN process models. By leveraging multi-agent workflows and RAG integration, your solution will combine domain knowledge with AI to produce accurate, high-quality models.
You'll implement a working prototype, deploy it online (e.g., on Azure), and showcase your results internally. To top it off, your work will be presented in an article shared online.
Objectives
* Develop a prototype supporting BPMN and DMN modeling standards
* Integrate domain knowledge using MCP and RAG for accurate process design
* Deploy the solution online and present results internally
* Publish an article summarizing your findings
Our offer
* Collaborative, international, and tech-driven environment
* Real impact: help analysts model processes smarter and faster
* Fun technical events: hackathons, brownbags, and our tech blog
* Monthly after-work events across locations
Skills required
* Knowledge of NLP and ML techniques, including deep learning
* Practical software development skills (Python, Java, or similar)
* Nice-to-have: familiarity with Azure or AWS services, foundational models
Additional information
* Internship / thesis starting in February 2026
* Applications must include your most recent academic transcripts
* Candidates must be completing a Master's degree and enrolled in a higher-education program with a valid internship agreement (convention de stage)