- Claude Skills & Agents: Hands-on building/maintaining them (or equivalent LLM agent frameworks) prompt engineering, tool use, context/skill design.
- Python + Playwright: Strong Python, solid Playwright for UI automation, framework creation experience
- Prompt-to-test-artifact design: Structuring prompts/skills to reliably turn user stories into structured test cases.
- Self-healing automation: Locator resilience, agile element detection, auto-repair logic.
- LLM evaluation: Judging/validating AI-generated code and tests for correctness rather than accepting output blindly.
- CI/CD: GitHub, TeamCity
- Version control: Git and code-review workflows.
- Practical automation testing experience and ownership of estimation and test strategy activities
- Real-world AI implementation experience, supported by specific project examples
- Accuracy and consistency of experience details across the resume and discussions
- The candidate’s ability to independently explain technical concepts and solutions