1214 | Senior Agentic QA Engineer

Intetics Inc.

Job Description

Quick Facts

  • Work Policy: Remote (Georgia)
  • Job Type: Full Time
  • Experience Level: Senior (8+ years in software QA, including 5+ years in test automation and 1+ years implementing agentic AI in production QA workflows)
  • Core Tech Stack: Playwright, Selenium WebDriver, Java, Python, TypeScript, Model Context Protocol (MCP / Playwright MCP), Claude Code, Cursor, GitHub Copilot, CI/CD, Git, SQL, API Testing

About Intetics Inc.

Intetics Inc. is a global technology company specializing in custom software application development, software product quality assessment, distributed professional engineering teams, and comprehensive digital solutions. For this engagement, you will support a premier cybersecurity client that builds advanced security platforms to safeguard sensitive systems and data against cyber threats. The client’s product suite spans compliance management, incident response, threat intelligence, and vulnerability management, helping organizations across diverse industries maintain secure digital environments.

About the Role

Intetics Inc. is hiring a hands-on Senior Agentic QA Engineer who has real-world experience integrating agentic AI workflows into an active quality assurance team. You will architect and build AI agents that collaborate directly with QA engineers—translating Jira tickets into structured test cases, authoring and maintaining Selenium and Playwright automated tests, conducting exploratory testing via Model Context Protocol (MCP), and triaging test failures inside CI pipelines.

Working closely with developers, product managers, and the QA Manager across engineering squads, you will establish the metrics, guardrails, and architectural patterns that govern where AI agents operate autonomously, where human review is mandatory, and how quality improvements are quantitatively proven.

What You’ll Do

Agentic QA Workflows

  • Architect, build, and operate AI agents spanning the full QA lifecycle, from ticket and requirement analysis through test case design, automated test generation, test execution, and failure triage.
  • Construct multi-agent workflows capable of taking a Jira ticket all the way to reviewed test cases and automated tests merged into continuous integration.
  • Leverage Model Context Protocol (MCP) servers—including Playwright MCP—to power self-healing locators, exploratory testing, and agent-led browser interactions.
  • Author, maintain, and version-control the skills, context files, tools, and prompts that power the QA agents just like production software code.
  • Establish clear human-in-the-loop checkpoints so agent-generated outputs receive human verification where necessary and earn autonomy where proven reliable.

Automation & Frameworks

  • Expand existing Selenium and Playwright test automation frameworks while spearheading a migration toward Playwright with AI agents handling the heavy lifting.
  • Utilize AI agents to convert manual regression suites into automated tests, steadily increasing test coverage without overburdening the QA team.
  • Author clean, maintainable, and reviewable automation code in TypeScript, Python, and Java adhering to established design patterns such as the Page Object Model (POM).
  • Embed agent-authored and agent-maintained test suites into CI/CD pipelines featuring parallel execution and transparent test reporting.

Quality & Reliability of the Agents Themselves

  • Design evaluation datasets and track core quality metrics for agent outputs, including time saved per release, flake rate, false-positive rate, and test case accuracy.
  • Validate AI agent tools and MCP servers directly, testing behavior when invoked by live AI agents alongside error handling, authentication and permissions, data accuracy, and tool responses.
  • Identify and eliminate low-value test coverage, brittle generated scripts, and hallucinated assertions.
  • Perform thorough root-cause analysis on test failures to distinguish genuine application bugs from agent errors, environment instability, or flaky tests.
  • Enforce security-first practices across all agent tooling, addressing prompt injection risks, strict data access boundaries, and secure secrets management.

Collaboration & Enablement

  • Collaborate with product managers, developers, and the QA Manager to pinpoint where AI agents deliver the highest impact within a weekly release cycle.
  • Mentor and enable fellow QA engineers to adopt agentic workflows daily through reusable templates, clear documentation, and hands-on pairing.
  • Communicate lessons learned, technical trade-offs, and measurable outcomes clearly to engineering leadership in plain, accessible language.

What You’ll Need

  • At least 8 years of professional software quality assurance experience, including 5 or more years focused on test automation.
  • A minimum of 1 year of hands-on experience embedding agentic AI into an actual QA team’s production workflow (beyond individual usage of a coding assistant).
  • Proven track record of building at least one AI agent or multi-agent pipeline that triages, executes, or generates tests in a live QA process, with the ability to explain how its performance was measured.
  • Practical experience working with AI coding agents (such as GitHub Copilot, Cursor, or Claude Code) and MCP servers (Playwright MCP or equivalent).
  • Strong software engineering proficiency across TypeScript, Python, and Java, producing reviewable, maintainable, and clean test code.
  • Extensive hands-on experience architecting and maintaining test automation frameworks in Selenium WebDriver and Playwright using design patterns like the Page Object Model.
  • Solid exploratory and manual testing foundation, paired with the judgment to determine when human testing outperforms automation.
  • Strong API testing background and practical SQL skills to validate backend data behind the user interface.
  • Hands-on experience running reliable automated suites in CI/CD pipelines and managing code with Git.
  • Sound judgment regarding where AI-generated outputs require human verification, plus the ability to articulate those trade-offs to leadership and engineers.
  • Advanced debugging skills with a demonstrated history of isolating root causes for intermittent or complex failures.
  • Self-starting ownership mindset with the versatility to wear multiple hats, learn new tools rapidly, coach peers, and iterate quickly using empirical measurements while balancing enthusiasm for AI agents with healthy skepticism.

Nice to Have

  • Hands-on experience developing custom agent tools or custom MCP servers rather than solely consuming existing ones.
  • Familiarity with agent development SDKs or frameworks such as OpenAI Agents SDK, LangGraph, or Claude Agent SDK.
  • Experience building LLM evaluation pipelines, including regression checks on prompts, scoring rubrics, and golden datasets.
  • Prior experience leading a migration from Selenium to Playwright.
  • Domain background in security-focused software, vulnerability management, or cybersecurity.
  • Knowledge of security testing methodologies and LLM-specific vulnerabilities such as data leakage and prompt injection.
  • Experience validating data-intensive platforms, ETL pipelines, or integrations involving Qualys, Tenable, ServiceNow, or Jira.
  • Experience mentoring QA professionals, delivering technical presentations, and working within Agile/Scrum teams shipping on a weekly or faster release cadence.

To apply for this job please visit jobs.workable.com.