Document Intelligence Engineer, Regulation and Contracts

• Design a record for each document type, with fields such as obligations, triggers, thresholds, exceptions, parties and deadlines.
• Build LLM extraction pipelines that propose each field together with the phrase it came from.
• Build the review screens where a reviewer accepts, corrects or rejects each proposed field.
• Compare document versions and record what changed, so each record links to the version it came from.
• Build obligation registers in which every obligation cites its clause.
• Measure extraction accuracy on reviewed samples, and report error patterns by field.
• Help state rules as properties a checker can test, with each counterexample traced back to its clause.
• Read scanned documents with OCR while keeping each field linked to its page and passage.

• 3+ years building production software in Python or TypeScript.
• Experience extracting structured data from text with LLMs or other language processing methods.
• Experience designing data schemas and versioning them.
• The patience to read legal, regulatory and contract text closely.
• Clear technical writing.

• Experience with regulatory, legal or contract data.
• Experience with formal methods, model checking or property-based testing.
• Experience with PostgreSQL and full-text search.
• Experience with OCR on scanned documents.

$124,000 to $201,000 a year

Full-time W-2 employment with health insurance, a retirement plan and paid leave.

No application deadline. We accept applications for this role on an ongoing basis.

Remote, United States