Назад
Company hidden
16 дней назад

Retrieval-Augmented Generation for Financial Regulation via LLM Orchestration and Hybrid Symbolic-Subsymbolic AI

Формат работы
onsite
Тип работы
fulltime
Грейд
trainee
Английский
c1
Страна
Luxembourg
Вакансия из списка Hirify.GlobalВакансия из Hirify Global, списка международных tech-компаний
Для мэтча и отклика нужен Plus

Мэтч & Сопровод

Для мэтча с этой вакансией нужен Plus

Описание вакансии

Текст:
/
TL;DR
Retrieval-Augmented Generation for Financial Regulation via LLM Orchestration and Hybrid Symbolic-Subsymbolic AI (RAG/LLM/AI): Building a production-grade RAG system for regulatory-document processing and compliance analysis with an accent on adaptive retrieval, document validation, multilingual embeddings, and vector database optimization. Focus on evaluating retrieval quality, prototyping graph-based and multi-agent workflows, integrating LLM backends, and implementing production monitoring.

Location: Belval, Esch-sur-Alzette, Luxembourg

Company

hirify.global is a research and technology organisation conducting applied research in AI, security, industrial and other scientific domains.

What you will do

  • Enhance retrieval algorithms with adaptive query-based weighting and advanced chunk optimization.
  • Build document validation, format detection, quality scoring, preprocessing, and retrieval evaluation pipelines.
  • Optimize vector database indexing for faster document ingestion.
  • Evaluate embedding models, cross-lingual retrieval for multilingual EU regulations, graph-based retrieval, and multi-agent orchestration.
  • Improve the Streamlit interface, integrate LLM backends, optimize prompts, and implement production logging and monitoring.

Requirements

  • Advanced degree or final-year Bachelor’s/Master’s studies in Computer Science, Data Science, Machine Learning, NLP, Information Retrieval, or a related quantitative field with strong ML coursework.
  • Strong Python programming skills, including reading and modifying more than 1,000 lines of existing code.
  • Understanding of vector spaces, cosine similarity, and basic machine-learning concepts.
  • Experience with at least one ML framework, such as scikit-learn or transformers.
  • Familiarity with data structures and algorithms.
  • Git proficiency for collaborative development.
  • Fluency in English and French, both oral and written; English and French at C1 level are specified.

Nice to have

  • Previous work with LangChain or similar retrieval systems.
  • Experience with NLP libraries such as spaCy, NLTK, or transformers.
  • Understanding of information-retrieval concepts including BM25, TF-IDF, and relevance scoring.
  • Experience with Streamlit or similar web frameworks.
  • Knowledge of evaluation methodologies for ML systems.
  • Other relevant languages.

Culture & Benefits

  • Six-month fixed-term internship contract with a 40-hour work week.
  • Research environment focused on impact, responsible innovation, entrepreneurship, and partnerships in Luxembourg and Europe.
  • Personalized learning programme, multicultural workforce, and inclusive work environment.
  • 32 days of paid annual leave, 11 public holidays, a 13-month salary, and statutory health insurance.

Hiring process

  • Submit an online application including a position-oriented motivation letter detailing relevant experience and a CV.
  • Applications must be submitted through the HR system; applications by email will not be considered.
  • Applications are reviewed continuously until the position is filled; nationality is requested for statistical purposes only.

Будьте осторожны

Если работодатель просит войти в их систему, используя iCloud/Google, прислать код/пароль, запустить код/ПО, не делайте этого. Это мошенники. Обязательно жмите «Пожаловаться» или пишите в поддержку. Подробнее в гайде →