AI Coding Agent Engineer, DataAnnotation Tech (Remote)
Worked as an AI coding agent engineer supporting benchmark-oriented evaluation and behavioral analysis of AI coding agents. Reviewed AI coding agent outputs against quality and requirement standards, and provided corrected solutions when results were insufficient. Focused on sourcing and building codebases from open-source projects to support agent evaluation workflows. • Built and reviewed benchmark designs and behavioral evaluation for AI coding models • Analyzed agent behavior and output quality relative to requirements • Produced correct/better code solutions when model outputs failed quality thresholds • Searched, read, and assembled open-source codebases to support testing