Вакансия из Hirify Global, списка международных tech-компаний Для мэтча и отклика нужен Plus
Пожаловаться
Зарплата и рынок
развернуть
По международному рынку данных пока нет
На СНГ рынке: $3.1к/мес ($2.2к - $4.3к)
87
Крутая вакансия
развернуть
Чётко очерченная роль сочетает разработку production RAG-системы с прикладными AI-исследованиями в финансовой проверке фондов, а сильный исследовательский работодатель и хорошие условия повышают привлекательность; срочный контракт на 18 месяцев ограничивает долгосрочную стабильность.
Контракт на срок
Современный AI-стек
Понятные задачи
Много отпуска
Прикладной AI
Мэтч & Сопровод
Для мэтча с этой вакансией нужен Plus
Подключить Plus
Описание вакансии
Текст:
Hirify AI/Оригинал
TL;DR
Engineer – Document Intelligence for Fund Due Diligence (AI): Building a production-grade RAG system for KYC and fund due diligence across heterogeneous financial documents with an accent on entity-centric retrieval, document understanding, and structured extraction. Focus on benchmarking financial-domain embeddings, designing knowledge-graph and multi-agent retrieval workflows, and implementing evaluation, monitoring, and audit trails for analyst decision support.
Location: Belval, Esch-sur-Alzette, Luxembourg; home working policy available but not remote
Gross salary: €6,000–€6,679 per month, paid over 13 months (€79,200–€86,800 annually)
Company
hirify.global (LIST) is a research and technology organisation conducting applied research and innovation across AI, security, industrial, built, natural and space environments.
What you will do
Build a production-grade RAG system for KYC and fund due diligence across prospectuses, KIDs, AML/KYC reports and SFDR disclosures.
Build evaluation frameworks for entity extraction, due diligence completeness and analyst decision-support quality; optimise vector database indexing and retrieval.
Benchmark financial-domain embedding models and explore cross-lingual retrieval for French, German and Luxembourgish regulatory variants.
Prototype knowledge-graph retrieval and multi-agent orchestration for cross-document fund, manager, counterparty and regulatory relationships.
Integrate LLM backends, structured-extraction prompts, production monitoring, logging and audit trails for compliance review.
Requirements
Master’s degree in Computer Science, Artificial Intelligence or a closely related field.
Preferably at least 2 years of relevant research or industry experience.
Experience with at least one ML framework, such as scikit-learn or transformers.
Familiarity with data structures and algorithms, and proficiency with Git for collaborative development.
Fluency in English and French, both oral and written.
Nice to have
Financial services background and experience with LangChain, LlamaIndex or similar retrieval and agent-orchestration frameworks.
Knowledge of multi-agent workflow frameworks, NLP and entity-extraction libraries applied to financial or legal text.
Understanding of BM25, TF-IDF, relevance scoring and ML evaluation methodologies.
Experience with React, Node or similar web frameworks; application-driven AI research experience.
Knowledge of AML/KYC frameworks, FATF guidelines, EU AML Directives or fund due diligence processes.
Experience with entity resolution or knowledge-graph construction across heterogeneous document sources.
Ability to work independently and collaboratively in interdisciplinary, multi-partner research environments.
Other relevant languages are an asset.
Culture & Benefits
Fixed-term, full-time contract for 18 months, with a 40-hour working week.
Flexible working hours and a home working policy, but the position is not remote.
32 days of paid annual leave, 11 public holidays, statutory health insurance and a 13-month salary.
Personalised learning programme, digital lunch vouchers and access to innovative infrastructures and laboratories.
Multicultural, inclusive and gender-friendly research environment with more than 60 nationalities represented.
Hiring process
Apply formally online through the HR system; applications by email will not be considered.
Submit a position-focused motivation letter, scientific CV with contact details, publication and patent list if applicable, and contact details for two references.
Applications are reviewed continuously until the position is filled; selected candidates may undergo background, export-control and criminal-record checks.
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 →