SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
Salary: USD 130,000 - 160,000 / annual
DEFCON AI is an insights company leveraging artificial intelligence, mathematical optimization, data analytics, and software engineering to optimize complex systems and help customers anticipate, assess, and mitigate disruptions.
You will join the analytics and AI engineering team as an Information Extraction Engineer, responsible for extracting structured facts from long, free-text, narrative, and semi-structured documents. The role operates within a secure government cloud environment where traceability is paramount—every extracted fact must be tied to the exact passage it came from, and nothing gets asserted without a citation a human reviewer can verify.
You'll work with an established extraction practice rather than building one from scratch. A senior practitioner on the team has set the approach, and your contribution will be sustained, consistent output at volume against messy, narrative documents that were never written with extraction in mind. You'll exercise judgment to flag what doesn't fit rather than force interpretations.
Key responsibilities include:
- 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 actually supports the extracted fact, treating missing or unsupported citations as defects
- Distinguish stated totals from derived sums in financial narratives, retaining contributing items and calculations for verification
- Consume recorded rule context supplied to model-assisted extraction, keeping cited facts and uncertainty separate from validity decisions
- Apply and extend the team's established extraction approach consistently across new document types
- Handle ambiguous, contradictory, or incomplete source text without forcing a single reading; flag it rather than guessing
- Work with entity resolution and retrieval teammates on what usable extracted facts need to carry downstream
This is a fully remote role with a later start date than the company's most urgent openings. They are sourcing now to ensure the seat is filled when work begins.
REQUIREMENTS:
- 3+ years extracting structured facts or data from unstructured, narrative text in a production setting
- Experience keeping extracted output traceable to its source
- Demonstrated ability to work with ambiguous or incomplete information without forcing conclusions
- Comfort with financial or regulatory narratives (preferred but not required based on excerpt)
- Ability to work independently within an established framework while flagging edge cases appropriately
