Applied Scientist, Document Understanding

You hold a PhD or Master's in Computer Science, AI, NLP, or a related field, with 3+ 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 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. 3+ years of post-degree industry experience shipping document understanding, information extraction, or knowledge graph systems into production — not research-only experience. Publication record at ACL, EMNLP, ICLR, NeurIPS, SIGIR, KDD, or equivalent. Production Python and experience 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. #J-18808-Ljbffr TempWorks Software Incorporated