Job Description

Responsibilities (developer)

• Design multi-agent QA workflows for test planning, test design, automation, execution, reporting, and defect analysis.
• Build reference architectures for AI-powered testing agents.
• Integrate testing agents with test management, automation, CI/CD, source control, defect tracking, and observability platforms.
• Define prompt libraries, RAG patterns, tool-calling workflows, and agent orchestration models.
• Establish review and approval workflows for AI-generated test cases and automation code.
• Define evaluation metrics for agent output quality.
• Create reusable patterns for API, UI, regression, performance, and exploratory testing agents.
• Support testing of AI and GenAI-based applications.
• Implement governance for data privacy, security, auditability, and responsible AI usage.
• Coach QA engineers on AI-assisted testing practices.
• Partner with leadership to define an AI-led QA transformation roadmap.

Required Experience

• Strong background in software testing and quality engineering.
• Hands-on test automation architecture experience.
• Programming experience in Python, Java, JavaScript, TypeScript, or C#.
• Experience with tools such as Selenium, Playwright, Cypress, REST Assured, Postman, Karate, Jenkins, GitHub Actions, Azure DevOps, Jira, TestRail, Zephyr, or equivalent.
• Understanding of LLMs, GenAI, prompts, agents, RAG, embeddings, tool calling, and guardrails.
• Experience integrating testing solutions into CI/CD pipelines.
• Strong understanding of QA metrics, defect lifecycle, test strategy, and release governance.
• Excellent communication, architecture documentation, and stakeholder-management skills.