ML Engineer, Retrieval & Grounded Generation

Role overview Establish quality engineering for an AI-enabled decision-support system, owning how product requirements become verifiable tests and release evidence. This is a hands-on role on the product side: you will build automation, assess system performance and decision quality, and independently determine whether a release meets its acceptance criteria.

Responsibilities - Maintain a system test plan covering functional, integration, performance, and load testing; clarify acceptance criteria with product before development starts. - Build automated tests from requirements, integrate them into CI/CD release gates, and maintain regression coverage and coverage reporting. - Coordinate customer acceptance testing and track findings through resolution. - Create labeled evaluation sets, run sampled audits, and measure both incorrect or missed results and user overrides. - Document how measures are calculated, what data supports them, and what evidence is needed for each release. - Track build, model, configuration, and threshold versions; produce release reports and rollback criteria, and confirm test environments are representative of production.

Requirements - Five or more years in software quality engineering, test automation, or software engineering with substantial test ownership. - Strong coding skills in an automation language and framework, such as Python with pytest or JavaScript/TypeScript with Playwright, Cypress, or Selenium; ability to reason about application code. - Experience building automated suites and integrating them into CI/CD release gates. - Experience owning a test plan through review and acceptance, including performance and load testing. - Demonstrated ability to test against product requirements, clarify what correct means with product owners or users, and report findings independently. - Routine use of AI-assisted development tools with sound judgment about validating their output.

Nice to have - Experience evaluating AI or machine-learning systems, including quality audits, citation checks, or analysis of disagreements with recommendations. - Work in high-consequence systems subject to external review; familiarity with responsible AI frameworks or accessibility standards.

Benefits and work setup - Fully remote, flexible, results-based work; occasional travel of up to 25% may be required. - Salary range listed as $135,000–$170,000, with bonus and equity. Benefits described include employer-paid medical, dental, and vision coverage, 14 weeks of paid parental leave, unlimited PTO with manager approval, and professional development support.