Lead Applied Scientist, Document Understanding

This is a fully remote position, open to applicants in United States, +4 more locations.

📋 Description

• Take ownership of the design, development, and deployment of document understanding systems that support Westlaw, PracticalLaw, and CoCounsel.

• Create and implement semantic chunking models for extensive, irregularly structured legal documents.

• Develop document enrichment systems utilizing both legal and customer-defined taxonomies.

• Construct LLM-based knowledge graph pipelines that extract and connect citations, entities, and legal concepts.

• Spearhead knowledge distillation initiatives to reduce large models into latency-sensitive, production-ready SLMs.

• Design evaluation frameworks at both component and end-to-end levels using expert annotations and synthetic data.

• Make technical decisions regarding architecture, chunking strategies, classification methods, and knowledge extraction techniques.

• Collaborate with engineering teams to ensure delivery, reliability, and scalability across various product lines.

• Offer technical insights to senior leadership on AI strategy and future directions.

• Guide and mentor applied scientists and machine learning practitioners.

⛳️ Requirements

• PhD in Computer Science, Artificial Intelligence, Natural Language Processing, or a related discipline.

• Over 8 years of industry experience in developing and scaling document understanding, information extraction, knowledge graphs, or applied NLP solutions.

• Proficiency across the complete ML lifecycle, including model development, evaluation, optimization, distillation, and production deployment.

• Strong skills in Python programming.

• Practical experience with PyTorch, Hugging Face Transformers, and DeepSpeed.

• Proven history of publishing research in prominent conferences such as ACL, EMNLP, ICLR, NeurIPS, SIGIR, KDD, or equivalent.

• Capability to mentor technical talent and achieve measurable business outcomes through production-ready AI solutions.

• Experience in translating advanced research into scalable, high-performance products and services.

• Excellent communication skills and ability to collaborate across functions.

• Extensive hands-on experience in document layout analysis and semantic chunking beyond fixed-size or paragraph-based methods.

• Significant hands-on experience in hierarchical, multi-label document classification using domain-specific and customer-defined schemas.

• In-depth production experience in entity recognition and linking, relation extraction, citation parsing, and constructing knowledge graphs from unstructured text.

• Extensive hands-on production experience with LLM-based information extraction, few-shot and multi-task learning, and post-training techniques.

• Comprehensive production experience in knowledge distillation, model compression, and SLM deployment in latency-constrained environments.

• Significant hands-on experience in synthetic data generation and designing annotation workflows.

• Extensive hands-on experience in designing end-to-end evaluation frameworks for document understanding.

• Preferred: Experience in legal document understanding, legal information extraction, or legal AI.

• Preferred: Knowledge of complex document structures, retrieval or QA systems, RAG and agentic workflows, knowledge graph frameworks, AzureML, or AWS SageMaker.

🏝️ Benefits

• Flexible work arrangements, allowing work from anywhere for up to 8 weeks each year.

• Flexible vacation policy.

• Two company-wide Mental Health Days off.

• Access to the Headspace app.

• Retirement savings plan.

• Tuition reimbursement program.

• Employee incentive programs.

• Resources for mental, physical, and financial well-being.

• Two paid volunteer days off each year.

• Comprehensive health, dental, vision, disability, and life insurance options.

• Competitive 401(k) plan with company matching.

• Paid sick and safe time off.

• Paid holidays.

• Parental leave benefits.

• Sabbatical leave opportunities.

• Optional hospital, accident, and sickness insurance.

• Optional life and AD&D insurance.

• Flexible Spending and Health Savings Accounts available.

• Fitness reimbursement program.

• Employee Assistance Program.

• Group Legal Identity Theft Protection benefit.

• Access to a 529 Plan.

• Commuter benefits.

• Adoption & Surrogacy Assistance.

• Employee Stock Purchase Plan.

• Annual bonus based on enterprise and individual performance (role may be eligible).