AI Trainer – Handshake AI
As an AI Trainer at Handshake AI, I developed and evaluated prompts to assess large language model (LLM) performance. My work focused on improving AI understanding of scientific and technical materials, providing expert-level feedback and analysis. I contributed by enhancing LLM capabilities in handling complex queries and multimedia content. • Evaluated LLM outputs for scientific accuracy, clarity, and depth • Developed domain- and context-specific prompts for LLM assessment • Reviewed and improved AI interpretations of images, videos, and audio • Conducted independent research to support evaluation and prompt development