Description
At ELCA, our consultants maintain enterprise solutions based on Microsoft Dynamics 365, analyzing bug tickets manually—a process that's time-consuming and depends heavily on experience.
In this thesis, you'll explore how AI and LLMs can revolutionize software maintenance. You'll build an AI-powered troubleshooting agent that learns from past tickets, source code, and documentation to suggest root causes and potential fixes, drastically reducing resolution times and helping support teams work smarter.
You'll join a collaborative, innovative environment with experienced mentors, modern tools, and real impact for customers and internal teams.
Objectives
* Ingest historical ADO tickets and source code to build a searchable AI knowledge base
* Automatically analyze new tickets and suggest root causes and code fixes
* (Bonus) Develop a lightweight web UI for support specialists to interact with the assistant
Our offer
* Collaborative, international, and tech-driven environment
* Real impact: improve enterprise software maintenance efficiency
* Fun tech events: hackathons, brownbags, and our technical blog
* Monthly after-work events across locations
Skills required
* AI & NLP/ML knowledge, experience with LLMs
* Programming: C# and JavaScript
* DevOps and version control concepts (Git)
* Nice-to-have: Azure DevOps, vector search, web development, Dynamics 365
Additional information
* 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)