Prompt Engineer & AI QA Specialist

Write, test, and systematically improve prompts for customer-facing agents-building evaluation sets that catch regressions before they reach production." , responsibilities:Design and iterate on system prompts, few-shot examples, and chain-of-thought structures.Build and maintain golden evaluation datasets per agent and deployment.Run adversarial and edge-case testing; document failure modes and mitigations.Collaborate with engineers to implement automated evaluation pipelines.requirements:2+ years working with LLMs in a product or research context.Structured approach to experimentation-hypothesis, test, measure, document.Python scripting for evaluation automation is a plus.