Senior Agentic QA Engineer

Intetics Inc., a global technology company providing custom software application development, distributed professional teams, software product quality assessment, and “all-things-digital” solutions, is seeking a highly skilled and experienced Senior Agentic QA Engineer to join our dynamic team.

The client is a leading company specializing in advanced cybersecurity solutions. They provide comprehensive security measures designed to protect sensitive data and systems from cyber threats. Their offerings include vulnerability management, threat intelligence, incident response, and compliance management. With cutting-edge technology and a team of experts, they ensure robust protection for organizations across various industries, helping clients stay ahead of evolving cyber threats and maintain a secure digital environment.

Role Overview

This is a 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.

You’ll partner with the QA Manager, developers, and product managers across engineering teams. You’ll set the patterns, guardrails, and metrics that decide where agents are trusted, where they need to review, and how we prove they’re actually improving quality.

What You’ll Do

Agentic QA Workflows

• 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

Automation & Frameworks

• Extend our 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

Quality & Reliability of the Agents Themselves

• 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

Collaboration & Enablement

• 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

• 8+ years in software quality assurance, with at least 5 years in test automation
• 1+ years of hands-on experience bringing agentic AI into a QA team’s real workflow, not just personal use of a coding assistant
• Built at least one agent or multi-agent workflow that generates, runs, or triages tests in a production QA process, and can explain how its output was measured
• Hands-on experience with MCP servers (Playwright MCP or similar) and with AI coding agents such as Claude Code, Cursor, or GitHub Copilot
• Strong programming skills in Java, Python, and TypeScript, with clean, maintainable, reviewable test code
• Deep hands-on experience building and maintaining automation frameworks in Playwright and Selenium WebDriver, and design patterns such as the Page Object Model
• Strong manual and exploratory testing skills, with the judgment to know when a human check beats an automated one
• Solid API testing experience and working SQL skills for validating data behind the UI
• Experience running automation reliably in CI/CD pipelines and with Git
• Sound judgment about where AI output needs human validation, and the ability to explain that trade-off to engineers and leadership
• Strong debugging skills, with a track record of driving complex or intermittent failures to root cause

Preferred Experience

• Experience building custom MCP servers or agent tools, not only using existing ones
• Experience with agent frameworks or SDKs (Claude Agent SDK, LangGraph, OpenAI Agents SDK, or similar)
• Experience designing evals for LLM output, including golden datasets, scoring rubrics, and regression checks on prompts
• Experience leading a Selenium-to-Playwright migration
• Experience in cybersecurity, vulnerability management, or security-focused products
• Familiarity with security testing and with LLM-specific risks such as prompt injection and data leakage
• Experience testing data-heavy platforms, ETL pipelines, or integrations with tools like Jira, ServiceNow, Tenable, or Qualys
• Experience presenting technical topics and mentoring QA engineers
• Background in Agile/Scrum with a weekly or faster release cadence

Common Skills & Traits

• Self-starter with a strong ownership mindset and the ability to wear multiple hats
• Curious and skeptical in equal measure: excited about what agents can do and honest about where they fall short
• Able to learn new tools quickly and coach them to others
• Willing to fail fast, measure, and iterate