Build reliable AI agents at TribalScale through software testing, test automation, and evaluation frameworks for dynamic applications. The location remains to be confirmed. As an Agentic QA Engineer, you will validate AI-powered applications and multi-step agentic workflows. You will write code, debug complex systems, and apply testing principles to nondeterministic outputs. The work includes functional, integration, regression, and end-to-end quality engineering.

Key Responsibilities
- Design testing strategies for AI agents and LLM-powered applications
- Build automated frameworks for functional and regression testing
- Measure accuracy, reliability, task completion, and consistency
- Test APIs, tool usage, and multi-step workflows




- Investigate hallucinations, incorrect calls, and workflow failures

Requirements:
- Qualified software QA, SDET, or testing-focused engineering experience
- Experience building automated tests and testing frameworks
- Understanding of API, integration, regression, and end-to-end testing
- Experience debugging complex technical issues
- Familiarity with Git and CI/CD pipelines Apply software quality engineering, automation, and analytical thinking to improve reliability across TribalScale’s AI-powered systems.

📌 Agentic QA Automation Engineer (Toronto)
🏢 TribalScale
📍 Toronto