Senior Applied Scientist, Document Understanding

Refinitiv; New York (NY); Hybrid; USD 127,400 - 236,600; Full time

Benefits offered by this job

Flexible vacation

Mental Health Days

Tuition reimbursement

Employee assistance programs

Fitness reimbursement

Job summary

Refinitiv is seeking a Senior Applied Scientist to design and build document understanding systems. This role involves working on semantic chunking models, document enrichment systems, and knowledge graph pipelines to deliver foundational intelligence in the legal domain.

The successful candidate will hold a PhD or Master's in a related field and have a strong background with 5+ years of industry experience. Benefits include flexible work arrangements, comprehensive health plans, and a salary range of $127,400–$236,600 USD.

Qualifications

• 5+ years of post‑degree industry experience shipping document understanding in production.
• Experience leading through influence in an applied research setting.
• Publications at ACL, EMNLP, ICLR, NeurIPS, SIGIR, KDD, or equivalent.

Responsibilities

• Design and deploy semantic chunking models for legal documents.
• Build document enrichment systems to classify documents.
• Develop knowledge graph construction pipelines for legal content.

Skills

Document understanding

Information extraction

Knowledge graph systems

Production Python

PyTorch

Hugging Face Transformers

Education

PhD or Master's in Computer Science, AI, NLP, or related field

Tools

DeepSpeed

Job description

About the Role

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

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 have hands‑on depth across model development, distillation, evaluation, and deployment. 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 Python and experience with PyTorch, Hugging Face Transformers, and DeepSpeed.

Production Experience 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.
• Experience with complex legal document structures: 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.
• Experience with AzureML or AWS SageMaker.

New Position

This position is open due to an existing vacancy to support our evolving business needs.

Benefits

• Flexibility & Work‑Life Balance: Flex My Way with supportive workplace policies, flexible work arrangements, and up to 8 weeks of work from anywhere per year.
• Career Development and Growth: Culture of continuous learning, skill development, and an AI‑enabled future growth path.
• Industry Competitive Benefits: Comprehensive plans including flexible vacation, two company‑wide Mental Health Days, Headspace app access, retirement savings, tuition reimbursement, employee incentive programs, and resources for mental, physical, and financial wellbeing.
• Inclusive Culture: Recognition for belonging, flexibility, work‑life balance, and alignment with core values.
• Social Impact: Two paid volunteer days annually and opportunities for pro‑bono consulting projects and ESG initiatives.
• Compensation: Base salary range $127,400–$236,600 USD (US) or $100,000–$145,000 CAD (Ontario); performance bonuses available.
• Additional Benefits: Optional hospital, accident, and sickness insurance (100% paid by employee); optional life and AD&D insurance (100% paid by employee); Flexible Spending and Health Savings Accounts; fitness reimbursement; Employee Assistance Program; Group Legal Identity Theft Protection (100% paid by employee); 529 Plan access; commuter benefits; Adoption & Surrogacy Assistance; Employee Stock Purchase Plan.

Equal Employment Opportunity Statement

Thomson Reuters is a proud Equal Employment Opportunity Employer, providing a drug‑free workplace, reasonable accommodations for qualified individuals with disabilities, and compliance with all applicable laws. We welcome applications from all qualified individuals regardless of race, color, sex/gender, pregnancy, gender identity and expression, national origin, religion, sexual orientation, disability, age, marital status, citizen status, veteran status, or any other protected characteristic.