Lead Applied Scientist, Document Understanding — Hybrid

Thomsonreuters; Schweiz; Hybrid; EUR 194.635 - 259.514; Vollzeit

Benefits dieser Stelle

Hybrid work model

Career development

Mental health & wellbeing benefits

Zusammenfassung

Thomson Reuters seeks a Lead Applied Scientist, Document Understanding to design and deploy semantic chunking and document enrichment pipelines across legal, tax, and accounting content.

You will lead the development of multi-label classification, information extraction, and knowledge graph construction, while mentoring applied scientists and guiding production-ready AI systems powering search, retrieval, and reasoning.

Qualifikationen

• PhD in Computer Science, AI, NLP, ML, Information Retrieval or related field with industry experience.
• Hands-on depth across document analysis, information extraction, classification, knowledge representation, evaluation and production deployment.
• Experience taking NLP/AI capabilities from research to production and building production document understanding systems.
• Ability to mentor applied scientists and drive production-ready AI initiatives.

Aufgaben

• Design and deploy semantic chunking systems for lengthy legal, tax and accounting documents.
• Build document enrichment pipelines to identify types, jurisdictions, entities and metadata.
• Develop hierarchical and multi-label document classification systems using standard and customer taxonomies.
• Lead development of AI pipelines for information extraction, knowledge graphs, and table understanding.
• Shape evaluation frameworks and mentor teams to deliver scalable, reliable solutions.

Kenntnisse

Document understanding

Information extraction

Classification

Knowledge representation

Production deployment

NLP

LLM integration

Ausbildung

PhD in Computer Science or related field

Jobbeschreibung

Thomson Reuters seeks a Lead Applied Scientist, Document Understanding to design and deploy semantic chunking and document enrichment pipelines across legal, tax, and accounting content.

You will lead the development of multi-label classification, information extraction, and knowledge graph construction, while mentoring applied scientists and guiding production-ready AI systems powering search, retrieval, and reasoning.