AI Fellow – Handshake AI
As a Handshake AI Fellow, I evaluated and refined large language model outputs. My responsibilities included creating high-quality annotations, prompts, and test cases to enhance AI datasets. I analyzed recurring failure patterns and provided actionable feedback to engineering and product teams. • Evaluated and rated AI-generated text outputs for platform alignment • Developed and documented prompts and test cases for model improvement • Collaborated with reviewers for workflow consistency in AI training • Provided feedback to optimize language model responses