QA for a fullstack agentic AI tool

we're building the future of agentic AI — autonomous systems that think, plan, and act. We're looking for a sharp QA Engineer who's excited about testing the kinds of systems that don't sit still. What You'll Do Design and execute test plans for agentic AI workflows, including multi-step autonomous tasks and tool-use pipelines Identify, document, and track bugs across the full product lifecycle Build and maintain automated test suites for both frontend and backend systems Evaluate AI agent outputs for accuracy, reliability, and edge case behavior Collaborate closely with engineers and product to define acceptance criteria Develop regression tests to ensure platform stability as features evolve What We're Looking For 2+ years of QA or software testing experience Familiarity with automated testing tools (Playwright, Selenium, Pytest, etc.) Strong analytical mindset with an eye for edge cases Bonus: experience testing AI/ML systems or LLM-powered products Clear communicator who can turn fuzzy bugs into crisp, reproducible reports