AI Agent Evaluation Analyst for Autonomous Agents (No coding required)

Candidates should be strong analytical thinkers with excellent attention to detail, fluent written English, and comfort reading structured data such as JSON or YAML. No coding background is required, but you must be comfortable reasoning about complex systems, spotting ambiguities, and writing clear documentation. Prior exposure to QA thinking, logic puzzles, or evaluation frameworks is a plus. Please submit your resume in English. You will review and refine agent evaluation tasks and scenarios, identify inconsistencies or missing assumptions, define gold standard behaviors, and annotate reasoning paths and plausible alternatives. You will collaborate with QA, writers, and developers to suggest refinements, expand edge case coverage, and ensure that autonomous agents are tested thoroughly and realistically. This is part time, fully remote work with flexible hours.

AI Training Project Overview