About this role
Defcon AI builds analytics and artificial intelligence platforms that leverage mathematical optimization and data analytics for resilient optimization of complex systems. The analytics and AI engineering team develops a system that ingests records from disparate sources, resolves entities, and displays the exact source text behind every answer. Operating within a secure government cloud environment, the platform requires extraction methods that remain verifiable against original documents.
Working within an established extraction practice, the incoming engineer extracts structured facts from long, free-text documents while ensuring every claim ties directly to its source passage. Responsibilities include handling ambiguous narrative text, applying model-assisted extraction rules, and collaborating with entity resolution and retrieval teammates. Ideal candidates bring dedicated experience with unstructured data and maintain consistent output quality at volume without forcing ambiguous readings.
What you will do
- Extract structured facts from long, free-text, narrative, and semi-structured documents.
- Maintain a traceable pointer from every extracted fact back to the exact source passage.
- Validate that every cited passage supports the extracted fact and treat missing citations as defects.
- Distinguish stated totals from derived sums in financial narratives by retaining contributing items and calculations.
- Apply and extend the team's established extraction approach consistently across new document types.
- Handle ambiguous, contradictory, or incomplete source text by flagging issues instead of guessing.
- Coordinate with entity resolution and retrieval teammates regarding downstream requirements for extracted facts.
What you need
- Bring three or more years of experience extracting structured facts or data from unstructured, narrative text in a production setting.
- Demonstrate hands-on experience keeping extracted output traceable to its source.
- Possess strong Python programming skills with practical experience in NLP or information extraction tooling.
- Maintain US citizenship.
- Hold an active US Secret clearance.
Nice to have
- 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
Benefits
- Competitive salary, bonus, and equity package
- 100% employer paid, comprehensive health insurance including medical, dental, and vision for employee and family
- Unlimited PTO, with manager's approval
- Flexible work environment where employees manage their work day
- 14 weeks of fully-paid parental leave
Skills and tech stack
Questions candidates ask
Is this position remote?
This is a fully remote role with a later start date than the most urgent openings. Defcon AI is sourcing now so the seat is filled when the work begins.
What is the salary range for this role?
The typical salary range for this position is $130,000 to $160,000. This represents the typical range based on experience, skills, and other factors.
What clearances are required?
US citizenship is required along with an active US Secret clearance. An active Top Secret clearance is preferred.