Remote job
Information Extraction Engineer
Job details
About this role
Role overview
Turn long, messy narrative and semi-structured documents into reliable, structured facts for a production information platform. The core of the role is making each fact verifiable: reviewers should be able to follow it back to the precise passage that supports it, while ambiguity and uncertainty remain visible.
Responsibilities
- Extract structured facts from varied documents and keep a precise source passage linked to each one. - Check that each citation supports its fact; flag missing, weak, or contradictory evidence instead of guessing. - Preserve the distinction between a total stated in a document and one calculated from component amounts, including the calculation and inputs. - Apply the established extraction approach consistently as new document types are introduced. - Use supplied rule context for model-assisted extraction while keeping evidence and uncertainty distinct from validity judgments. - Coordinate with entity resolution and retrieval colleagues on the information downstream systems need.
Requirements
- At least three years extracting structured information from unstructured or narrative text in a production setting. - Experience maintaining traceability from extracted output to its source. - Strong Python skills and practical experience with NLP or information extraction, using rule-based, statistical, or language-model methods. - U.S. citizenship and an active Secret clearance.
Nice to have
- Extraction experience in government, investigations, legal work, financial crime, or intelligence-related settings. - Language-model extraction using structured schemas, with outputs checked against source text. - Experience supplying extracted facts to matching, scoring, or retrieval systems. - An active Top Secret clearance.
Benefits and work setup
The position is fully remote, with a flexible, results-focused work environment. The listed compensation range is $130,000–$160,000, with potential bonus and equity. Benefits include employer-paid medical, dental, and vision coverage for employees and their families, manager-approved unlimited paid time off, and 14 weeks of paid parental leave.