AI Internship: Legacy Code Modernization

We are ELCA, one of the largest Swiss IT tribe with over 2,200 experts. We are multicultural with offices in Switzerland, Spain, France, Vietnam and Mauritius. Since 1968, our team of engineers, business analysts, software architects, designers and consultants provide tailor-made and standardized solutions to support the digital transformation of major public administrations and private companies in Switzerland. Our activity spans across multiples fields of leading-edge technologies such as AI, Machine & Deep learning, BI/BD, RPA, Blockchain, IoT and Cyber Security.

• Research and compare agentic AI approaches that combine LLM-driven agents with static and program analysis to mine business rules from legacy code.
• Select the most promising approach and AI engines, including options beyond LLMs.
• Design and build a prototype agent that navigates a representative legacy .NET/VB6 codebase on its own and cross-references related modules.
• Extract and document business rules, turning knowledge that only lives in the code into a clear specification that experts can review.
• Add mechanisms that flag uncertain findings for expert review.
• Validate your results with domain experts and use their feedback to improve the agent.
• Propose a repeatable methodology and best practices for using agentic knowledge mining before modernization, replacement or retirement decisions.
• Lay the groundwork for a scalable Legacy Modernization Assessment offering for clients across the market.

• A dynamic, collaborative workplace with a highly motivated, multicultural team working across international sites
• Monthly AI meetups with our expert AI team, where you can ask questions and move your topic forward
• The chance to make a difference in people's lives by building innovative solutions
• Internal coding events such as Hackathons and Brownbag sessions, plus our technical blog
• Monthly After-Works organized at each location

• Bachelor or Master degree (EPFL, ETH, university) in Computer Science or related discipline
• You have programming experience in .NET
  , and ideally some knowledge of VB6/ (or you're happy to learn).
• You are familiar with static code analysis.
• You have worked with different AI engines, LLMs and beyond.
• You are curious about agentic AI and keen to build your own agent.
• You like to work in a structured way and to share your findings clearly with experts.
• You are fluent in written and spoken English, as well as German or French.

We believe in strong values and are convinced that diversity is the key to success. If you take on challenges with curiosity, motivation and drive, you've come to the right place! Let our motto inspire you:
We make it work!