Agentic QA Engineer (Remote)

The Role

We run a portfolio of more than 500 sites and products, built and maintained with a team of AI agents. Before anything reaches users, someone has to check it actually works and feels right.

You'll test our sites and apps with AI agents doing much of the legwork. You write the prompts that drive the checks, review what the agents find, and catch what they miss: broken flows, sign-in problems, layouts that look off, and anything that makes the experience feel clumsy.

Not sure this role fits yet? Try Find the Gap, our 45-minute AI hackathon, or look at the paid-on-results traineeship, where you run one of our products end to end.

What You'll Do

• ▶ Write and refine prompts that make AI agents test our sites and apps properly
• ▶ Run end-to-end checks of real user journeys: sign-up, sign-in, forms, checkout and settings
• ▶ Review agent findings, confirm real issues and throw out false alarms
• ▶ Report bugs clearly, with steps to reproduce and a screenshot
• ▶ Judge visual and UX quality, and say plainly when a page looks or feels poor
• ▶ Test across multiple accounts and social logins

Who You Are

• ✓ Good at prompting AI tools in a testing context, with some agentic prompt-engineering experience
• ✓ High familiarity with ChatGPT, Claude and Meta's Muse
• ✓ You understand the difference between unit, integration and end-to-end testing
• ✓ Digitally savvy: you know how sign-in works, including SSO and OAuth
• ✓ Comfortable with browser tools, extensions and plugins
• ✓ Experience managing multiple accounts, including social media accounts
• ✓ Strong attention to detail
• ✓ A good eye for design: you can tell good user and visual design from poor
• ✓ You care about a seamless experience that feels smart and personal
• ✓ Clear written English for async work in Discord

Details