At Handshake AI, I evaluate AI systems for reasoning, factual accuracy, instruction adherence, and response quality. I use structured rubrics to compare text, image, and multimodal outputs, and review contributor submissions for accuracy and guideline compliance.
At Stellar AI, I train and evaluate agents on reasoning, web navigation, software interaction, and multistep workflows. I also completed 575+ usability studies at UserTesting and support research for multiple clients through data analysis, literature reviews, and technical reporting.

