4 hours ago
Remote, United StatesMid Level
Base Salary
$130k - $160k/yr
Responsibilities
- Extract structured facts from long, free-text, narrative, and semi-structured documents.
- Maintain a traceable pointer from every extracted fact to the exact source passage.
- Validate that cited passages support extracted facts and identify missing or unsupported citations as defects.
- Distinguish stated totals from derived sums while retaining contributing items and calculations for verification.
- Consume recorded rule context for model-assisted extraction while separating cited facts and uncertainty from validity decisions.
- Apply and extend the established extraction approach consistently across new document types.
- Handle ambiguous, contradictory, or incomplete source text by flagging issues instead of guessing.
- Collaborate with entity-resolution and retrieval teammates on downstream requirements for extracted facts.
Requirements
- At least 3 years of production experience extracting structured facts or data from unstructured, narrative text.
- Experience maintaining traceability between extracted output and its source.
- Strong Python skills with hands-on NLP or information-extraction tooling using rule-based, statistical, or LLM-based approaches.
- US citizenship is required.
- An active US Secret clearance is required.
- Preferred qualifications include government, investigative, legal, financial-crime, or intelligence-adjacent extraction experience; LLM-based extraction with structured schemas and source validation; downstream matching, scoring, or retrieval experience; and an active Top Secret clearance.
Benefits
- Fully remote, results-based work environment.
- Competitive salary, bonus, and equity package.
- Employer-paid comprehensive medical, dental, and vision insurance for the employee and family.
- Unlimited PTO with manager approval.
- Flexible work environment with control over the workday.
- 14 weeks of fully paid parental leave.
About DEFCON AI
DEFCON AI builds AI-driven simulation and decision-support software for logistics, mobility, and supply chain operations. Its platform uses mathematical optimization, machine learning, and data science to help organizations plan, assess risk, and keep missions and shipments moving during disruptions; current work includes delivering capabilities for the U.S. federal government. Founded in 2022 and headquartered in McLean, Virginia, the company is privately held and raised a seed round in 2024.