INT-26036-IN RETRIEVAL-AUGMENTED GENERATION FOR FINANCIAL REGULATION VIA LLM ORCHESTRATION AND HYBRID SYMBOLIC-SUBSYMBOLIC AI

The Luxembourg Institute of Science and Technology (LIST) is a leading Research and Technology Organisation (RTO) that drives innovation for the economy and society in Luxembourg and beyond. With cutting-edge expertise in Natural, Built, Industrial environments, Space, AI, Security and defence technologies. LIST bridges scientific excellence and applied research to design solutions that address real-world challenges and create positive impact.

Do you want to know more about LIST? Check our website: 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 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 in all that we do
• An environment encouraging curiosity, innovation and entrepreneurship in all areas
• Personalized learning programme to foster our staff’s soft and technical skills
• Multicultural and international work environment with more than 60 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, 11 public holidays, 13-month salary, statutory health insurance

Internship contract | Belval | 6 Months

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

How will you contribute?

You'll be working on a production-grade Retrieval-Augmented Generation (RAG) system that processes regulatory documents and serves as a critical tool for compliance analysis. You will contribute to create a multi-layered system with real performance requirements and measurable impact

Code Development (60%):

• Enhance the retrieval algorithm by implementing adaptive weighting based on query characteristics
• Add comprehensive document validation pipeline with format detection, quality scoring, and automatic preprocessing
• Implement advanced chunk optimization strategies.
• Build evaluation frameworks to systematically measure retrieval performance
• Optimize vector database indexing pipeline for faster document ingestion

Research & experimentation (25%):

• Test different embedding models against the current Nomic Embed Text baseline
• Explore cross-lingual capabilities for multilingual EU regulatory documents
• Research and prototype graph-based retrieval for document relationships
• Experiment with multi-agent systems and workflow orchestration platforms.

System integration (15%):

• Enhance the Streamlit interface with advanced filtering and search capabilities
• Integrate new LLM backends and optimize prompt engineering
• Implement comprehensive logging and monitoring for production deployment

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

Education

• Advanced degree (Master’s or Bachelor’s final year) in Computer Science, Data Science, Machine Learning, NLP, Information Retrieval, or related quantitative field with strong ML coursework

Experience and skills

Must Have:

• Strong Python programming (you'll be reading and modifying 1000+ lines of existing code)
• Understanding of vector spaces, cosine similarity, and basic ML concepts
• Experience with at least one ML framework (scikit-learn, transformers, etc.)
• Familiarity with data structures and algorithms
• Git proficiency for collaborative development

Highly valued:

• Previous work with LangChain, or similar retrieval systems
• Experience with NLP libraries (spaCy, NLTK, transformers)
• Understanding of information retrieval concepts (BM25, TF-IDF, relevance scoring)
• Experience with Streamlit or similar web frameworks
• Knowledge of evaluation methodologies for ML systems

Language skills

• Fluency in English (and French), both oral and written. Other relevant languages are an asset.