Information Extraction Engineer

Role overview

Establish quality engineering for an AI-enabled decision-support system, with responsibility for verifying that releases meet product-defined acceptance criteria. This product-side role combines test strategy, software development for automation, evaluation of system outcomes, and release governance. It works closely with engineering while maintaining independent evidence of product quality.

Responsibilities - Own a system test plan spanning functional, integration, performance, and load testing; review requirements early and make acceptance criteria verifiable. - Build automated test suites, integrate them into CI/CD release gates, maintain regression coverage, and report against an agreed coverage standard. - Plan customer acceptance testing and track findings through resolution while holding delivery teams to documented criteria. - Build labeled evaluation sets, conduct sampled audits of automated decisions, and measure both missed results and user overrides. - Document how quality measures are calculated, what data supports them, and what evidence is required for each release. - Maintain version records for builds, models, configurations, and thresholds; prepare test reports, evaluation records, and rollback criteria.

Requirements - At least five years in software quality engineering, test automation, or software engineering with substantial test ownership. - Strong coding ability in a test automation language and framework, such as Python with pytest or JavaScript/TypeScript with a browser automation framework; ability to read and reason about application code. - Experience building automated suites and integrating them into CI/CD as release gates. - Experience owning a test plan and testing against product requirements, including working with product owners or end users to define correct behavior. - Experience with performance and load testing, including interpreting what results demonstrate. - Regular use of AI-assisted development tools with sound judgment about reviewing and verifying generated work.

Nice to have

Experience evaluating AI or machine-learning systems, creating labeled datasets, assessing decision quality, or working in high-consequence domains with external review. Familiarity with responsible AI governance or accessibility standards is also useful.

Benefits and work setup

Fully remote, results-based work with occasional travel of up to 25% to headquarters, customer sites, or vendor facilities. Listed benefits include salary, bonus and equity, employer-paid medical, dental and vision coverage, flexible scheduling, unlimited PTO with manager approval, and 14 weeks of paid parental leave. The stated salary range is $135,000–$170,000.