INT-26031 ASSESSMENT OF TRUSTWORTHINESS IN LARGE LANGUAGE MODELS AND AI AGENTS

The Luxembourg Institute of Science and Technology (LIST) is a Research and Technology Organization (RTO) active in the fields of materials, environment and IT. By transforming scientific knowledge into technologies, smart data and tools, LIST empowers citizens in their choices, public authorities in their decisions and businesses in their strategies. https://www.list.lu/ 

Your LIST benefits

• An organization with a passion for impact and strong RDI partnerships in Luxembourg and Europe that works on responsible and An organization with a passion for impact and strong RDI partnerships in Luxembourg and Europe that works on responsible and independent research projects;
• Sustainable by design, empowering our belief that we play an essential role in paving the way to a green society;
• Innovative infrastructures and exceptional labs occupying more than 5,000 square metres, including innovations such as our Viswall, high-scale incubators and top of the range 3D/4D printings that are part of our toolkit for excelling in all we do;
• Multicultural and international work environment with more than 45 nationalities represented in our workforce;
• Diverse and inclusive work environment empowering our people to fulfil their personal and professional ambitions;
• Gender-friendly environment with multiple actions to attract, develop and retain women in science;
• 32 days’ paid annual leave for a full time internship, 11 public holidays per annum, flexible working hours,
• An environment encouraging curiosity, innovation and entrepreneurship in all areas.

Internship contract – 6 months | Fulltime/40h | From 01.03.2026 on | Belvaux

Are you passionate about research? So are we! Come and join us

How will you contribute?

The trainee will work within the LIST AI Technical Sandbox (https://ai-sandbox.list.lu/), an innovative environment dedicated to the trustworthiness evaluation of LLMs and AI Agents. The traineeship will focus on supporting the development, integration and validation of software components used to assess fairness, robustness and responsible behaviour in AI systems.

This traineeship offers an opportunity to gain hands-on experience in software engineering for trustworthy AI, contributing to both frontend and backend modules that operationalise AI evaluation workflows.

Key Tasks:

• Collaborate with engineers and researchers to design and implement features supporting the assessment of trustworthiness dimensions such as fairness, robustness and safe behaviour in LLMs and AI Agents.
• Contribute to the development and integration of components within the AI Technical Sandbox ecosystem.

Expected Deliverables:

• Development and testing of new assessment modules for LLMs and AI Agents and/or extension of existing ones.
• Contributions to interfaces or APIs that operationalise trustworthiness evaluation workflows within the AI Technical Sandbox.

Is Your profile described below? Are you our future colleague? Apply now!

Education

• Master in computer science

Experience and skills

• Python (LLMs, AI agents and data science libraries)
• Streamlit nice to have

Language skills

• Good command of English