This role owns quality for LOIS for Word, Filevine's AI-powered legal drafting product. You'll help build and own the QA function: the test strategy, the process, and the automation. You'll work at the intersection of legal AI and product quality, evaluating everything from AI output accuracy to UI behavior across the product. A big part of this role is moving quality upstream, so it's built into how features are planned and shipped from the start.
The ideal candidate has 2+ years of QA experience, brings a sharp eye for both functional bugs and AI quality issues, is comfortable building from scratch in ambiguity, and gets genuinely uncomfortable shipping something they haven't tried to break.
What You'll Do:
-
Define and own the test strategy, process, and QA playbook for the product
-
Move QA upstream by partnering with product and engineering early, so test plans are ready before features ship
-
Evaluate AI output quality across dimensions like accuracy, citation reliability, and appropriately scoped reasoning
-
Design and maintain evaluation sets that account for non-deterministic output and catch regressions over time
-
Test how AI-generated edits apply to documents, including accuracy and formatting fidelity across document structures
-
Build automated guardrails integrated into CI/CD that cover critical flows
-
Write structured, reproducible bug reports
-
Partner with legal domain experts to understand how different customer types use the product, and translate that into test coverage
-
Approach QA with a product and design mindset. If something works but could be better, we want to hear it
-
Compare behavior across product surfaces and document discrepancies
What You'll Need:
-
2+ years of QA experience, including ownership of test strategy for a product or major feature area
-
Track record of building QA process and automation from scratch in a fast-moving environment
-
Comfort operating in high ambiguity, where features ship quickly and you figure out how to test them fast
-
Strong analytical and problem-solving skills, with attention to both functional correctness and AI output quality
-
Ability to reason about non-deterministic systems and define what "correct" means when there's no single right answer
-
Excellent written communication, with the ability to write clear, concise, actionable bug reports backed by evidence
-
Experience with bug tracking tools and test management workflows
Nice To Have:
-
Experience testing AI or LLM-based products, especially for output accuracy and eval design
-
CI/CD experience setting up pipelines and release gates for automated tests
-
A design or UX sensibility, with an eye for where product workflows could be smoother
-
Prior experience in legal technology or comfort reading legal contracts
-
Programming experience beyond test automation
The salary range represents the low and high end of the salary range for this position. The total compensation package for this position will be determined by each individualβs location, qualifications, education, work experience, skills and performance.
An individualβs final offer will be weighted by their primary work location and expertise.