AI Quality Engineer

About Zemingo

Zemingo designs, builds, and scales digital products and services used by millions, partnering with leading global enterprises and high-growth innovators. We operate inside complex ecosystems, mature design systems, and multidisciplinary teams. We're reimagining our entire engineering and delivery lifecycle for the AI era - replacing legacy bottlenecks with intelligent, agentic systems.

• Why Zemingo?
• Ship at Scale: Work on real, production-grade applications that touch millions of daily active users.
• Autonomous Engineering Culture: Join a studio that values deep technical curiosity, proactive ownership, and systems architecture over manual repetition.
• Pioneer the Standard: Help define how modern quality engineering operates when autonomous agents, LLMs, and code generation lead the testing lifecycle.

What you'll be doing

• Architect Autonomous QA Agents: Design, code, and deploy AI-driven testing agents that dynamically generate test cases, execute exploratory passes, and autonomously heal broken end-to-end regression runs.
• Build Robust Modern Automation: Develop and scale reliable, fast-executing test suites using Playwright and TypeScript/Python across complex web applications and API ecosystems.
• Validate Non-Deterministic AI Features: Build evaluation and benchmarking frameworks to test client-facing LLM capabilities, including output accuracy, prompt drift, edge cases, and hallucination guardrails.
• Deep Root-Cause Analysis: Work directly alongside product engineers and architects to isolate transient bugs, trace failure modes in distributed systems, and improve automated triage workflows.
• Advance Native Mobile Quality: Collaborate with mobile teams to introduce modern, AI-assisted testing paradigms to iOS and Android builds.

Requirements

• Software Development & Scripting: Good coding skills in TypeScript/JavaScript or Python, with the ability to build test utilities, script against APIs, and integrate external libraries cleanly.
• Modern E2E Test Automation: 2+ years of hands-on experience building, scaling, and maintaining automated test suites using Playwright (or Cypress).
• Practical AI Engineering: Demonstrable experience working directly with LLMs (OpenAI, Anthropic, open-source models), prompt chaining, or emerging agentic web tools.
• QA & Systems Thinking: Strong foundational understanding of software testing methodologies, API testing (REST/GraphQL), test data management....
• Curiosity & Proactive Mindset: An active builder who experiments with new developer tools, agentic workflows, and emerging AI paradigms before they become industry consensus.
• Communication & Collaboration: Excellent technical communication skills, capable of bridging product requirements, developer context, and quality standards.

Advantages (Nice to Have)

• Hands-on experience with native mobile automation frameworks (e.g., Maestro, Appium).
• Experience with agentic frameworks or orchestration engines (e.g., LangChain, CrewAI, AutoGen, or LangGraph).