Senior Applied Scientist, Document Understanding

Das ist der Job

You have hands‑on depth across model development, distillation, evaluation, and deployment.

Darum lohnt es sich

You will work across semantic chunking, document enrichment, and knowledge graph construction for complex legal, tax, and accounting content — delivering foundational intelligence that multiple product teams depend on at scale.

Benefits Flexibility & Work‑Life Balance: Flex My Way policies support personal and professional responsibilities, including up to 8 weeks of remote work per year. Industry Competitive Benefits: Comprehensive plans covering flexible vacation, mental health days, Headspace app, retirement savings, tuition reimbursement, and wellbeing resources.

Culture: Inclusion, belonging, and values that emphasize customer focus, competition, challenge, speed, and teamwork.

Senior Applied Scientist, Document Understanding About the Role This is an applied science position focused on designing, building, and deploying production‑grade document understanding systems that power Westlaw, PracticalLaw, and CoCounsel.

About You You hold a PhD or Master’s in Computer Science, AI, NLP, or a related field, with 5+ years of post‑degree industry experience shipping document understanding, information extraction, or knowledge graph systems into production.

You work independently, lead through influence in an applied research setting, and measure success by what ships and performs in production. What You’ll Do Design and deploy semantic chunking models for lengthy, non‑uniformly structured legal documents with adjustable granularity across use cases.

Build document enrichment systems that classify documents according to legal and customer‑defined taxonomies and extract rich metadata. Develop LLM‑based knowledge graph construction pipelines that extract and link citations, entities, and legal concepts across diverse legal content.

Build scalable synthetic data generation systems for model training, multi‑hop query simulation, and hallucination‑free answer generation. Apply knowledge distillation techniques to compress large models into latency‑constrained, production‑ready SLMs.

Design evaluation frameworks — component‑level and end‑to‑end — using expert annotation and synthetic data. Drive independent technical decisions on chunking strategy, classification approach, knowledge extraction methods, and multi‑document reasoning architecture.

Partner with engineering on delivery, reliability, and scale across multiple product lines. Contribute to published research at venues such as ACL, EMNLP, ICLR, NeurIPS, SIGIR, and KDD, and to intellectual property.

Required Qualifications PhD or Master’s in Computer Science, AI, NLP, or a related field. 5+ years of post‑degree industry experience shipping document understanding, information extraction, or knowledge graph systems into production — not research‑only experience. Publications at ACL, EMNLP, ICLR, NeurIPS, SIGIR, KDD, or equivalent.

Experience leading through influence in an applied research setting. Production‑level Python experience and familiarity with PyTorch, Hugging Face Transformers, and DeepSpeed. Hands‑on Production Depth Required In Document layout analysis and semantic chunking beyond fixed‑size or paragraph‑based methods.

Hierarchical, multi‑label document classification with domain‑specific and customer‑defined schemas. Entity recognition and linking, relation extraction, citation parsing, and knowledge graph construction from unstructured text. LLM‑based information extraction, few‑shot and multi‑task learning, and post‑training.

Knowledge distillation, model compression, and SLM deployment under latency constraints. Synthetic data generation for NLP: query‑answer generation with verification and scalable data augmentation. Annotation workflow design and evaluation framework development for document understanding tasks.

Preferred Qualifications Legal document understanding, legal information extraction, or legal AI applications. Complex document structures common in legal content: nested hierarchies, cross‑references, non‑uniform formatting, and embedded elements. Retrieval, QA, or analysis systems over large document collections.

Knowledge graph frameworks for legal or enterprise applications. RAG and agentic workflows for enterprise knowledge systems. AzureML or AWS SageMaker experience. Career Development and Growth: Continuous learning programs, skill‑first approach, and opportunities to lead and thrive in an AI‑enabled future.

Social Impact: Two paid volunteer days per year and opportunities for pro‑bono consulting and ESG initiatives. Impact: Helping customers pursue justice and truth on a global scale. Compensation Base compensation range: $127,400 USD – $236,600 USD (U.S.). For Ontario, Canada: $100,000 CAD – $145,000 CAD.

Base pay is positioned within the range based on experience and internal equity. Annual bonus may be awarded based on enterprise and individual performance.

Equal Employment Opportunity Statement We are an Equal Employment Opportunity Employer and welcome applicants regardless of race, color, sex/gender, sexual orientation, disability, age, or any other protected classification under applicable law.

We provide reasonable accommodations for qualified individuals with disabilities and sincerely held religious beliefs. Closing Date This job posting will close 07/23/2026. #J-18808-Ljbffr