AI Quality Engineer

Start.io is a mobile marketing and audience platform that empowers the mobile app ecosystem by simplifying mobile marketing, audience building, and mobile monetization. It integrates with over 500,000 monthly active mobile apps to provide access to global first-party data for behavior analysis, opportunity identification, and growth.

• 5+ years of hands-on experience in Software Quality Engineering, Test Automation, or Software Engineering.
• Strong experience with test automation frameworks such as Playwright, Cypress or similar.
• Strong programming skills in JavaScript, TypeScript, or Python.
• Hands-on experience building AI-powered tools, applications, workflows, or agents using LLMs.
• Practical understanding of agentic workflows, prompt and context engineering, tool calling, MCP, and API integrations.
• Experience turning experimental solutions into reliable and maintainable engineering products.
• Strong QA fundamentals, including test design, regression testing, and exploratory testing.
• Experience with APIs, databases, and distributed systems.
• Experience with CI/CD systems such as GitHub Actions, Jenkins, or similar.
• Strong problem-solving skills and ability to independently drive technical initiatives.

Nice to Have:

• Experience evaluating LLM or agent output and measuring AI solution quality.
• Experience building internal developer, engineering, or QA platforms.
• Experience with observability and distributed systems.
• Experience integrating AI with tools such as GitHub, Jira, Confluence, or CI/CD platforms.
• Experience with Kubernetes or cloud infrastructure.
• AdTech or programmatic advertising experience.

• Design, build, and evolve AI-powered tools, agents, and workflows to improve QA team efficiency and quality.
• Identify repetitive or high-impact QA activities and develop scalable AI-enabled solutions.
• Build integrations between AI capabilities and testing, engineering, and internal systems.
• Define technical standards and best practices for AI-powered QA solutions, including prompts, context, tool usage, agent workflows, and human-in-the-loop processes.
• Build mechanisms to evaluate AI output, measure quality, and detect regressions.
• Monitor and improve the reliability, performance, and cost of AI-powered solutions.
• Act as the technical focal point for AI within the QA team, promoting adoption, knowledge sharing, and experimentation.
• Collaborate closely with QA engineers and engineering teams to develop practical, real-world AI solutions for QA challenges.