On independent remote projects, I evaluate AI-generated outputs and benchmark tasks for accuracy, completeness, and instruction compliance. I also audit live-web tasks for reproducibility and clear success criteria.
I review annotated data and task outputs, identify errors and edge cases, and document evaluation decisions. I create structured grading rubrics and JSON schemas to support consistent, reproducible AI evaluation.
Through independent visual projects, I’ve developed videography and video-editing skills, working with Adobe Premiere Pro, After Effects, CapCut, and DaVinci Resolve. I also apply visual-content review and annotation to AI and data evaluation workflows.
