All roles with salary

Principal Quality Engineer (AI-Assisted & Agentic Testing)

Modus Create MexicoEst. Est. USD 6,500–9,500 / monthLead

Estimated range based on role, country and industry — not published by the company.

Key requirements

  • Java
  • Ci/Cd
  • Llm
  • Consulting
Principal Quality Engineer (AI-Assisted & Agentic Testing) About Us Founded in 2011, Modus is a global, fully remote team of world-class technologists who thrive in a collaborative, innovative environment. We’re a digital product engineering partner for forward-thinking businesses. Our global teams work side-by-side with clients to design, build, and scale custom solutions that achieve real results and lasting change, partnering with industry leaders including AWS, GitHub, and Atlassian. We were fully remote before it was cool! Recognized as one of the Inc. 5000 Fastest Growing Private Companies for nine years and a top remote work company by FlexJobs, we have helped some of the world’s largest brands deliver powerful digital experiences. As an award-winning Atlassian partner with a world-class team, we help organizations innovate and solve complex challenges for Fortune 500 companies and beyond, we want to hear from you. Opportunity! We are looking for a Principal Quality Engineer to help transform quality engineering practices by introducing AI-assisted testing, agentic automation, and modern quality engineering frameworks within complex enterprise environments. You'll work directly within a client's engineering team, assessing existing testing practices, building scalable automation solutions, and leveraging Claude Code and AI coding agents to accelerate test creation, regression testing, and quality validation. This is a highly hands-on engineering and consulting role that combines advanced test automation expertise with agentic AI development practices . You'll contribute directly to production testing initiatives, develop reusable AI-assisted testing workflows, and mentor QA engineers and developers through practical collaboration and hands-on pairing. You'll also work across enterprise applications involving COBOL systems, Java/Spring middleware, and TypeScript/React frontends , helping ensure quality across integrated, mission-critical systems. Requirements: 10+ years of professional experience in Quality Assurance, Test Automation, Software Development Engineering in Test (SDET), or related software engineering roles. Strong hands-on experience designing and building test automation frameworks from scratch , using tools such as Playwright, Cypress, or similar technologies . Advanced expertise in API testing, integration testing, end-to-end testing, and automated regression testing . Hands-on experience using Claude Code, Claude CLI, GitHub Copilot, or AI coding agents to generate, review, refactor, and maintain automated tests. Experience configuring agentic testing workflows , including prompts, custom skills, repository memory files, guidelines, and reusable AI-assisted testing patterns. Proven experience converting manual regression suites into automated tests , particularly within existing enterprise applications. Strong experience integrating automated tests into CI/CD pipelines , using GitHub Actions, Jenkins, or similar tools. Solid understanding of test strategy, risk-based testing, test data management, coverage analysis, and flaky-test diagnosis . Ability to critically evaluate AI-generated test cases and scripts , identifying incomplete coverage, incorrect assumptions, unreliable assertions, and potential security risks. Experience establishing guardrails and validation processes to ensure AI-generated tests meet production-quality standards, including secure handling of credentials, dependencies, and sensitive data. Experience defining, tracking, and improving quality engineering metrics , such as automation coverage, test creation time, regression cycle time, flaky-test rates, and escaped defects. Familiarity with testing AI-powered applications , including evaluating LLM-generated outputs for accuracy, consistency, hallucinations, and non-deterministic behavior. Understanding of Agentic AI Evaluations (Evals) , including evaluation datasets, scoring criteri

See your match score for this role.

Xecodai maps the interview stages and shows what is preventing a 95% match.

Analyse this role