AI Training & Evaluation – Project Diamond (Handshake AI)
In Project Diamond for Handshake AI, I annotated and evaluated AI-generated responses to ensure alignment with project guidelines. My work focused on maintaining consistency and high standards in evaluating the quality of outputs. I applied detailed analysis to provide actionable feedback for ongoing model improvement. • Evaluated and rated large language model (LLM) responses • Checked outputs for consistency, relevance, and guideline adherence • Contributed to structured dataset curation for training and testing • Collaborated remotely with interdisciplinary AI teams