Назад
Company hidden
2 дня назад

Senior Agentic QA Engineer (AI)

Формат работы
remote (только Europe)
Тип работы
fulltime
Грейд
senior
Английский
b2
Страна
Poland/Armenia/Romania +3 еще
Вакансия из списка Hirify.GlobalВакансия из Hirify Global, списка международных tech-компаний
Для мэтча и отклика нужен Plus

Мэтч & Сопровод

Для мэтча с этой вакансией нужен Plus

Описание вакансии

Текст:
/
TL;DR
Senior Agentic QA Engineer (AI): Building AI-driven QA workflows that analyze Jira tickets, generate and maintain Playwright and Selenium tests, explore applications through MCP, and triage CI failures with an accent on agent evaluation, human-in-the-loop controls, and reliable automation. Focus on designing multi-agent testing pipelines, measuring test accuracy and flakiness, investigating complex failures, and applying security safeguards to agent tooling.

Location: Remote from Georgia, Armenia, Poland, Estonia, Azerbaijan, or Romania

Company

hirify.global provides custom software development, distributed professional teams, software product quality assessment, and digital solutions; this role supports a client developing cybersecurity products for vulnerability management, threat intelligence, incident response, and compliance management.

What you will do

  • Design, build, and run AI agents covering requirement analysis, test case design, test generation, execution, and failure triage.
  • Build multi-agent pipelines that transform Jira tickets into reviewed test cases and automated tests integrated into CI.
  • Use MCP servers, including Playwright MCP, for browser interaction, exploratory testing, and self-healing locators.
  • Extend Selenium and Playwright frameworks, support the Selenium-to-Playwright migration, and convert manual regression cases into automation.
  • Integrate agent-generated tests into CI/CD with parallel execution and clear reporting.
  • Define agent guardrails, human-review checkpoints, evaluation metrics, security controls, and enablement practices for QA engineers.

Requirements

  • 8+ years in software quality assurance, including at least 5 years in test automation.
  • At least 1 year of hands-on experience bringing agentic AI into a real QA team workflow.
  • Built at least one production agent or multi-agent workflow that generates, runs, or triages tests, with measurable output evaluation.
  • Hands-on experience with MCP servers and 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 experience building and maintaining Playwright and Selenium WebDriver automation frameworks and using patterns such as Page Object Model.
  • Strong manual, exploratory, API, and CI/CD testing skills; working SQL skills for validating data behind the UI; and experience with Git.
  • Sound judgment about human validation of AI output, strong debugging skills, and a record of driving complex or intermittent failures to root cause.

Nice to have

  • Experience building custom MCP servers or agent tools and using agent frameworks or SDKs such as Claude Agent SDK, LangGraph, or OpenAI Agents SDK.
  • Experience designing LLM evaluations with golden datasets, scoring rubrics, and prompt regression checks.
  • Experience leading a Selenium-to-Playwright migration or testing data-heavy platforms, ETL pipelines, Jira, ServiceNow, Tenable, or Qualys integrations.
  • Cybersecurity, vulnerability management, security testing, or security-focused product experience, including prompt injection and data leakage risks.
  • Experience presenting technical topics, mentoring QA engineers, and working in Agile/Scrum teams with weekly or faster releases.

Culture & Benefits

  • Remote work is available from the listed countries.
  • Work closely with the QA Manager, developers, product managers, and engineering leadership.
  • Support QA enablement through pairing, documentation, reusable templates, and technical knowledge sharing.
  • Operate with ownership, curiosity, skepticism, fast iteration, measurement, and continuous improvement.

Будьте осторожны

Если работодатель просит войти в их систему, используя iCloud/Google, прислать код/пароль, запустить код/ПО, не делайте этого. Это мошенники. Обязательно жмите «Пожаловаться» или пишите в поддержку. Подробнее в гайде →