Senior AI Scientist: Document Understanding & KG (Remote)

Thomson Reuters; Ann Arbor (MI); On-site; USD 140,000 - 210,000; Full time

Benefits offered by this job

Flexible work options

Tuition reimbursement

Mental health and well‑being programs

Volunteer days

Job summary

Thomson Reuters is seeking a Senior Applied Scientist, Document Understanding to design, build, and deploy production‑grade document understanding systems powering Westlaw, PracticalLaw, and CoCounsel. You will work on semantic chunking, document enrichment, and knowledge graph construction for complex legal content.

You have a PhD or Master’s and 5+ years shipping document understanding or knowledge graph systems, with hands‑on experience in PyTorch, Transformers, and model deployment in

Qualifications

• PhD or Master’s in CS/AI/NLP or related field with 5+ years post‑degree industry experience.
• Production experience shipping document understanding or knowledge graph systems.
• Publications at ACL, EMNLP, ICLR, NeurIPS, SIGIR, KDD or equivalent venue.

Responsibilities

• 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.

Skills

Production Python

PyTorch

Hugging Face Transformers

DeepSpeed

Leading through influence

Education

PhD or Master’s in CS/AI/NLP

Tools

AzureML

AWS SageMaker

Knowledge graph frameworks

Job description

Thomson Reuters is seeking a Senior Applied Scientist, Document Understanding to design, build, and deploy production‑grade document understanding systems powering Westlaw, PracticalLaw, and CoCounsel. You will work on semantic chunking, document enrichment, and knowledge graph construction for complex legal content.

You have a PhD or Master’s and 5+ years shipping document understanding or knowledge graph systems, with hands‑on experience in PyTorch, Transformers, and model deployment in