- 4+ years in QA with a clear bias toward automation and tooling over manual execution.
- Strong hands-on experience with Playwright (or equivalent modern framework — Cypress, etc.) for UI and API automation.
- Proficiency in JavaScript/TypeScript and API testing with Postman/Insomnia . ● Working fluency in LLM-powered development workflows (Claude Code, Cursor, Copilot, or similar) for test generation, debugging, and review.
- Grasp of AI/ML fundamentals — prompt engineering, context management, and evaluating LLM outputs for correctness and reliability.
- Comfort in an agent-driven workplace where AI agents are first-class collaborators across coding, testing, and operations.
- Treats AI agents as collaborators, not tools — knows when to trust, verify, or override their output.
- Solid SQL for data validation and a working understanding of API/backend test lifecycles.
- CI tooling experience (GitHub Actions,
Jenkins).
- Agile/Scrum experience and clear async communication for remote, cross-functional work.
Nice to Have ● Built MCP servers or custom Claude skills/tools to extend AI agent capabilities.
● Exposure to agentic test orchestration — autonomous agents that plan, execute, and adapt test runs based on code or requirement changes.
● Familiarity with AI-based observability and anomaly detection for proactive regression monitoring.