Senior Agentic QA Engineer
Hands-on role for a senior QA automation engineer who has already brought agentic workflows into a real QA team. You'll design and build AI agents that work alongside our QA engineers: turning Jira tickets into test cases, generating and maintaining Playwright and Selenium tests, exploring the application through MCP, and triaging failures in CI.
- Remote, United States +5 more
- Full-time
- Remote
- Posted Nov 15, 2026
INDUSTRYSoftware & InternetSaaS & Enterprise SoftwareCybersecurity
Locations (6)
- Georgia, United States
- Armenia
- Poland
- Estonia
- Azerbaijan
- Romania
Responsibilities
- Design, build, and run AI agents that cover the QA lifecycle: requirement and ticket analysis, test case design, test generation, execution, and failure triage
- Build multi-agent pipelines that take a Jira ticket through to reviewed test cases and automated tests merged into CI
- Use Model Context Protocol (MCP) servers, such as Playwright MCP, for agent-driven browser interaction, exploratory testing, and self-healing locators
- Build and maintain the prompts, tools, context, and skills our agents rely on, and version them like any other code
- Define human-in-the-loop checkpoints so agent output is reviewed where it matters and trusted where it has earned it
- Extend automation frameworks in Selenium and Playwright, and help drive our Playwright migration with agents doing the heavy lifting
- Use agents to convert manual regression cases to automation, keeping coverage growing without overloading the QA team
- Write clean, reviewable test code in Java, Python, and TypeScript, following patterns such as the Page Object Model
- Integrate agent-generated and agent-maintained tests into CI/CD pipelines with parallel execution and clear reporting
- Build evaluation sets and metrics for agent output: test case accuracy, false positive rate, flake rate, and time saved per release
- Experience testing MCP servers or AI agent tools, including tool responses, data accuracy, auth and permissions, error handling, and behavior when called by real AI agents
- Detect and reduce hallucinated assertions, brittle generated tests, and low-value coverage
- Investigate failures to root cause, telling product defects apart from test instability, environment issues, and agent mistakes
- Apply security-minded practices to agent tooling, including secrets handling, data access limits, and prompt injection risk
- Partner with the QA Manager, developers, and product managers to decide where agents add the most value in our weekly release cycle
- Teach QA engineers to work with agents day to day through pairing, documentation, and reusable templates
- Share results, trade-offs, and lessons learned with engineering leadership in plain terms
Requirements
- Experience in a Cybersecurity
Nice to have: Custom MCP server building, Agent frameworks (Claude Agent SDK, LangGraph, OpenAI Agents SDK), LLM evaluation design, Selenium-to-Playwright migration, Cybersecurity, Prompt injection testing
Skills
Agentic AITest AutomationPlaywrightSelenium WebDriverJavaPythonTypeScriptPage Object ModelAPI testingSQLCI/CDJiraPlaywright MCPClaude CodeCursorGitHub CopilotGit
More jobs nearby
Full description
Company details are for members
Sign up for a free job alert to see Intetics's profile, website and LinkedIn, and the same for every employer on Referso Jobs.