Lead Applied Scientist, Document Understanding
Core
Build state-of-the-art semantic chunking, document enrichment, and knowledge graph construction systems to serve as the cognitive foundation for legal AI products like Westlaw and CoCounsel.
Role type
Lead Applied Scientist (Document Understanding)
Builds
Semantic chunking systems, document enrichment pipelines, classification systems, information extraction pipelines, and knowledge graph construction systems for legal, tax, and accounting content.
Domain
Legal AI, Tax, Accounting, Information Retrieval
Deliverable
production ML models
Required skills
Document understanding, semantic chunking, document enrichment, hierarchical multi-label classification, information extraction (NLP/LLM), knowledge graph construction, tabular data understanding, evaluation framework design, technical leadership, production deployment
Preferred skills
Mentoring applied scientists, transforming unstructured documents into structured knowledge assets, building knowledge graphs from real-world content, extracting insights from complex tabular content
Technologies
LLMs, NLP, Knowledge Graphs, RAG
Responsibilities
Design and deploy semantic chunking systems for non-uniformly structured documents; Build document enrichment pipelines to identify metadata; Develop classification systems using standard and customer-defined taxonomies; Build LLM-based and traditional NLP information extraction pipelines; Develop knowledge graph construction systems; Design systems for extracting insights from complex tabular data; Create document intelligence capabilities for search, retrieval, RAG, and agentic AI; Design robust evaluation frameworks; Lead technical decisions on document analysis architectures; Partner with engineering teams to deliver scalable AI systems; Provide technical leadership and input into AI strategy; Mentor applied scientists and ML practitioners.
Seniority
Lead, hands-on IC with mentorship responsibilities