AI Evaluation Contributor
As an AI Evaluation Contributor at Handshake AI, I assessed the outputs of text, image, and audio models using established quality rubrics. My work involved identifying and categorizing errors, inconsistencies, and edge cases to support iterative model improvement. I provided detailed, structured written reports to inform development teams and maintain high annotation standards. • Evaluated multimodal AI outputs for correctness, coherence, tone, and instruction-following • Applied rubric-based scoring and documented objective quality feedback • Identified hallucinations and inconsistencies to enhance AI accuracy and reliability • Maintained independent, deadline-driven workflow in a remote environment.