Senior Applied Scientist, NLP/GenAI(m/w/x)

Requirements

• PhD in CS, AI, NLP, or related field, or Master's with equivalent experience
• 5+ years experience building/deploying document understanding systems, IE pipelines, or KG construction
• Ability to translate complex document understanding problems into AI applications
• Professional experience scaling and leading in applied research
• Strong programming skills (Python) and modern deep learning frameworks experience
• Publications at relevant venues (ACL, EMNLP, ICLR, NeurIPS, SIGIR, KDD)
• Deep understanding of document understanding fundamentals
• Expertise in knowledge extraction and knowledge graph construction
• Expertise in LLM-based information extraction, few-shot/multi-task learning, post-training/knowledge distillation
• Solid understanding of synthetic data generation for NLP
• Solid understanding of efficiency optimization (knowledge distillation, model compression, SLM solutions)
• Solid understanding of DL/ML approaches for NLP
• Experience designing annotation workflows, creating labeled datasets, and evaluation frameworks
• Prior work on legal document understanding, IE, knowledge representation, or legal AI
• Prior work handling complex legal document structures
• Experience building systems for analysis, Q&A, or retrieval across large document collections
• Experience with knowledge graph frameworks for legal/enterprise applications
• Understanding of RAG and agentic workflows
• Publications at relevant venues (ACL, EMNLP, ICLR, NeurIPS, SIGIR, KDD)
• Experience with AzureML or AWS SageMaker

Tasks

• Design, build, test, and deploy AI solutions for legal document understanding.
• Develop advanced models for semantic chunking of legal documents.
• Build document enrichment systems for classification and metadata extraction.
• Create LLM-based knowledge graph construction pipelines.
• Develop scalable synthetic data generation systems.
• Simulate complex legal research queries.
• Generate hallucination-free answers.
• Collaborate with engineering for software delivery.
• Ensure software reliability at scale.
• Develop comprehensive data and evaluation strategies.
• Leverage human annotation and synthetic data for evaluation.
• Apply robust training and evaluation methodologies.
• Balance model performance with latency requirements.
• Apply knowledge distillation techniques.
• Compress large models into efficient SLMs.
• Optimize and deploy efficient SLM solutions.
• Determine architectures for semantic chunking.
• Address diverse document formats and structures.
• Adapt chunking granularity.
• Determine architectures for document classification.
• Support varying legal taxonomies and customer schemas.
• Determine architectures for LLM-based knowledge extraction.
• Handle citation errors and contextual references.
• Determine architectures for multi-document reasoning.
• Generate synthetic multi-hop queries.
• Balance accuracy, efficiency, and scalability.
• Solve real-world document challenges.
• Handle diverse document formats and content types.
• Partner with Engineering and Product teams.
• Translate legal document challenges into solutions.
• Engage stakeholders across product lines.
• Understand use case requirements.
• Shape objectives for document understanding.
• Align capabilities with diverse business needs.
• Support next-generation search and legal research.
• Maintain scientific and technical expertise.
• Demonstrate expertise through product deliverables.
• Publish research at top venues.
• Contribute to intellectual property.

Work Experience

Education

Languages

Tools & Technologies