• 3+ years extracting structured facts or data from unstructured, narrative text in a production setting
• Experience keeping extracted output traceable to its source
• Strong Python, with hands-on NLP or information-extraction tooling, whether rule-based, statistical, or LLM-based
• US Citizenship Required
• Active US Secret clearance
• Extraction experience in a government, investigative, legal, financial-crime, or intelligence-adjacent setting
• LLM-based extraction with structured output schemas and validation against source text
• Experience where extracted facts fed a downstream matching, scoring, or retrieval system
• Active Top Secret clearance
• What Success Looks Like
• Facts extracted at volume, with every claim traceable to its source passage
• Extraction that holds up when a subject-matter expert checks it against the original document
• Sustained throughput across new document types without re-deriving the approach for each one