21 Nov
|
TribalScale
|
Toronto
21 Nov
TribalScale
Toronto
Test LLM-powered applications at TribalScale using automation, API validation, and failure analysis for complex agent interactions. The location remains to be confirmed. As an Agentic QA Engineer, you will assess applications whose outputs are agile, nondeterministic, and dependent on multi-step reasoning. Your work will cover agent tool usage, external systems, integrations, and production behavior. Experience with AI agents or generative AI products is especially relevant. Key Responsibilities:
Validate agent tools, APIs, and external system interactions Design end-to-end testing strategies for agentic workflows Reproduce unexpected outputs and tool-use failures Apply automated quality checks to development pipelines Improve agent behavior through production findings Requirements:
Professional QA, quality engineering, SDET, or software engineering experience Experience with automated testing and framework development Understanding of API and end-to-end testing Experience debugging complex applications Familiarity with Git and CI/CD pipelines Use software testing, automation, and AI application knowledge to strengthen LLM workflow quality and reliability at TribalScale.
📌 LLM Application Test Engineer (Toronto)
🏢 TribalScale
📍 Toronto