Lead AI Scientist, Document Understanding

Reuters; Zug; Hybrid; CHF 150.000 - 230.000; Vollzeit

Zusammenfassung

Thomson Reuters seeks a Lead Applied Scientist, Document Understanding, to advance semantic chunking and enrichment across legal, tax, and accounting content. You will build multi-label classifiers, knowledge graphs, and robust extraction pipelines that scale to large document collections and support downstream search and RAG workflows.

You will mentor teams, shape architecture choices, and partner with engineers to deliver production-grade AI capabilities that directly impact professional

Qualifikationen

• PhD in Computer Science, AI, NLP, ML, Information Retrieval, or related field.
• Hands-on depth across document analysis, information extraction, classification, knowledge representation, evaluation, and production deployment.
• Experience bringing NLP/AI capabilities from research to production and delivering business impact.

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 classification systems using taxonomies and multi-label approaches.
• Create NLP information extraction pipelines for entities, relationships, and citations.
• Construct knowledge graphs from large document collections and connect concepts across content.
• Develop systems to extract structured data from complex tabular content.
• Lead evaluations and collaborate with engineers to deliver production-ready AI systems.

Kenntnisse

Semantic chunking

Document enrichment

Knowledge graph

NLP information extraction

Classification

Evaluation frameworks

Production deployment

Mentoring

Ausbildung

PhD in Computer Science or related field

Jobbeschreibung

Thomson Reuters seeks a Lead Applied Scientist, Document Understanding, to advance semantic chunking and enrichment across legal, tax, and accounting content. You will build multi-label classifiers, knowledge graphs, and robust extraction pipelines that scale to large document collections and support downstream search and RAG workflows.

You will mentor teams, shape architecture choices, and partner with engineers to deliver production-grade AI capabilities that directly impact professional