Principal Quality Engineer (AI-Assisted & Agentic Testing)
Контакты
Формат работы
remote (только Mexico)
Тип работы
fulltime
Грейд
senior
Английский
b2
Страна
Mexico
aitypescripttest automationapi testingci cdqa automationcypressplaywrightllm evaluationagentic ai
Вакансия из Hirify Global, списка международных tech-компаний Для мэтча и отклика нужен Plus
Пожаловаться
Зарплата и рынок
развернуть
По международному рынку данных пока нет
На СНГ рынке: $2.5к/мес ($2к - $4к)
82
Хорошая вакансия
развернуть
Роль хорошо очерчена и дает заметную самостоятельность в быстро развивающемся направлении AI-тестирования, но консалтинговый формат может означать смену клиентских проектов.
?Клиентские проекты
?Высокая планка
Фокус на AI
Современный стек
Самостоятельность
Мэтч & Сопровод
Для мэтча с этой вакансией нужен Plus
Подключить Plus
Описание вакансии
Текст:
Hirify AI/Оригинал
TL;DR
Principal Quality Engineer (AI-Assisted & Agentic Testing) (AI-assisted test automation and enterprise quality engineering): Building production-ready automation frameworks and agentic testing workflows for complex enterprise applications with an accent on Playwright or Cypress, API and end-to-end testing, and AI-generated test validation. Focus on evaluating LLM outputs, establishing security guardrails, integrating tests into CI/CD pipelines, and mentoring QA engineers and developers.
Location: Remote, Mexico
Company
hirify.global is a global digital product engineering partner founded in 2011, delivering custom solutions for forward-thinking businesses and enterprise clients.
What you will do
Assess existing testing practices and introduce AI-assisted testing, agentic automation, and modern quality engineering frameworks.
Design and build scalable, production-ready test automation frameworks and convert manual regression suites into automated tests.
Use Claude Code and AI coding agents to generate, review, refactor, and maintain tests.
Integrate automated testing into CI/CD pipelines and establish guardrails for secure, production-quality AI-generated tests.
Evaluate AI-powered applications and LLM-generated outputs for accuracy, consistency, hallucinations, and non-deterministic behavior.
Mentor QA engineers and developers through hands-on pairing and collaborative development.
Requirements
10+ years of professional experience in quality assurance, test automation, SDET, or related software engineering roles.
Hands-on experience designing and building test automation frameworks from scratch with Playwright, Cypress, or similar technologies.
Advanced experience in API, integration, end-to-end, and automated regression testing, including conversion of manual regression suites into automated tests.
Hands-on experience with Claude Code, Claude CLI, GitHub Copilot, or other AI coding agents, including agentic testing workflows, prompts, custom skills, repository memory files, guidelines, and reusable patterns.
Experience integrating automated tests into CI/CD pipelines using GitHub Actions, Jenkins, or similar tools.
Knowledge of test strategy, risk-based testing, test data management, coverage analysis, flaky-test diagnosis, and quality engineering metrics.
Experience evaluating AI-generated tests, identifying coverage gaps, incorrect assumptions, unreliable assertions, security risks, and handling credentials, dependencies, and sensitive data securely.
Understanding of Agentic AI Evaluations, including evaluation datasets, scoring criteria, reliability measurements, and human review processes.
Experience mentoring and upskilling QA engineers and developers, plus strong communication and consulting skills.
Working knowledge of Git, Jira, and test management platforms such as Xray, TestRail, or Zephyr; exposure to COBOL, mainframe, legacy enterprise, or financial services systems.
Nice to have
Experience testing COBOL systems of record integrated with Java/Spring and modern frontend technologies.
Experience building custom Claude Code agents, testing skills, prompt libraries, reusable AI-assisted QA toolkits, or LLM evaluation frameworks.
Experience extracting business rules from legacy applications and using AI for test data generation, failure triage, regression test selection, or defect analysis.
Background in financial services, lending, account servicing, or other regulated enterprise environments.
Experience introducing AI-assisted quality engineering across multiple teams and developing QA playbooks, technical documentation, or enablement programs.
Experience measuring the impact of AI-assisted testing on productivity, software quality, and delivery efficiency.
Culture & Benefits
Fully remote work within Mexico as part of a global team.
Hands-on collaboration with client engineering teams and practical knowledge sharing.
Autonomy to define testing strategies, tooling configurations, and quality engineering improvements.
Opportunity to build reusable AI testing toolkits, custom agent skills, prompts, and validation guardrails.
Focus on measurable improvements in test coverage, regression cycle times, software quality, and engineering capabilities.
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 →