Senior ai test automation engineer

We are looking for a hands-on Senior AI Test Automation Engineer to design, build, and maintain automated testing solutions while applying modern AI and agentic engineering practices to the QA lifecycle. This is an engineering-first role combining strong test automation expertise with hands-on AI engineering. You will own automation across UI, API, and integration layers, embed testing into CI/CD, and use AI agents, MCP, agent skills, and evaluation harnesses to accelerate test generation, maintenance, analysis, and defect triage.

Responsibilities

• Build and own automated tests across UI (Playwright, Selenium), API, and service-integration layers
• Design end-to-end and integration test suites, keeping them fast, stable, and maintainable
• Integrate automated testing into CI/CD using GitLab, with automated regression, quality gates, and actionable reporting
• Expand automated regression coverage and reduce manual testing across high-volume and high-risk areas
• Investigate test failures and defects through triage, reproduction, root-cause analysis, and fix verification
• Apply data validation, reconciliation, and performance testing where appropriate
• Build and apply AI-assisted and agentic testing workflows for test generation, maintenance, analysis, and defect triage
• Develop reliable AI testing harnesses, evaluation workflows, and guardrails to make AI-assisted engineering repeatable and trustworthy

Requirements

• 3+ years of hands-on experience with test automation, particularly UI automation using Playwright and/or Selenium
• Experience with REST API testing and end-to-end/integration testing of web and service-based systems
• Proficiency in TypeScript/JavaScript, Java, or Python
• Experience integrating automated tests into CI/CD pipelines, preferably GitLab
• Experience with TestRail or similar test management tools and Jira
• Strong debugging and root-cause analysis skills
• Proven hands-on experience applying AI tools and agentic approaches in real engineering delivery, not just experimentation
• Skills in MCP (Model Context Protocol), building and/or integrating MCP servers and tools
• Expertise in authoring and packaging reusable agent skills for coding and testing agents
• Background in designing multi-step, semi-autonomous agentic workflows for AI-assisted test generation, maintenance, and defect triage
• Daily hands-on experience with AI coding agents such as Codex, Claude Code, and/or GitHub Copilot
• Competency in designing evaluation, testing, and agent harnesses with guardrails and feedback loops, along with hands-on experience with LangGraph and/or LangChain, and evaluating, monitoring, and improving AI-assisted engineering and testing workflows
• English proficiency at B2 level or higher