Quality Assurance Engineer

WE ARE HIRING ABOUT MEMORAE AI Memorae AI is building the next generation of AI-powered workspaces and personal assistants, products that think alongside you, remember what matters, and help you do your best work. We're a small, mission-driven team that moves fast, ships often, and cares deeply about the quality of what we build. THE ROLE We're looking for a QA Engineer who's as comfortable writing automated tests as they are probing an AI system for unexpected behaviour.

You'll own quality across our product, from API contracts to end-to-end user flows, and play a critical role in ensuring our AI features are reliable, accurate, and safe to ship. At Memorae, QA is a product function, not just a gatekeeping one. WHAT YOU'LL DO Design and maintain a test strategy covering automated, manual and AI-specific testing needs.

Build and maintain automated test suites using Playwright or Cypress for end-to-end flows. Test APIs thoroughly using Postman or REST clients, including edge cases, auth flows, and error handling. Evaluate LLM output quality, accuracy, consistency, tone, and safety, across different prompts and agent flows.

Define and track quality metrics, and flag regressions before they reach production. Work closely with engineers to shift testing left, catching issues early in the development cycle. Write clear, reproducible bug reports and help triage issues by priority and impact.

WHAT WE'RE LOOKING FOR 2–4 years of QA experience across manual and automated testing. Hands-on experience with Playwright or Cypress for browser-based automation. Strong API testing skills, REST, Postman, response validation, and negative test cases.

Exposure to or genuine curiosity about testing AI/LLM systems, prompt sensitivity, hallucinations, output drift. Analytical mindset, you find edge cases others miss and think in systems, not just test cases. Ability to communicate quality issues clearly to both technical and non-technical stakeholders.

NICE TO HAVE Experience building evaluation frameworks or benchmarks for LLM output quality. Basic scripting ability in JavaScript or Python for test tooling or data generation. Familiarity with CI/CD pipelines and integrating tests into deployment workflows.

Prior experience at a startup or AI-first product company. AREAS OF FOCUS Automated testing · Playwright/Cypress · API testing · Postman · LLM output quality · AI eval frameworks · Regression testing · Bug triage WHY MEMORAE AI Own the quality culture from the ground up, this is not a ticket-closing role. Work on genuinely novel QA challenges, testing AI systems is a frontier problem with no playbook.

Small team where your voice directly influences how the product is built and tested. Fast-paced environment where good processes you build actually stick.