Annotator for AI Evaluation Specialist & Domain Expert Products — Handshake AI
Evaluated and approved AI-generated scientific papers for content and technical accuracy as a domain expert. Assessed model outputs for inaccuracies, vagueness, and missing information that non-technical reviewers might overlook. Produced clear structured feedback and written annotation rationales as part of evaluation workflows. • Reviewed AI science content for correctness, completeness, and domain validity • Wrote organized justifications for evaluation and annotation decisions • Supported analysis using scientific figures and data visualization elements (e.g., spectra and microscopy outputs) • Collaborated on prompt optimization and reliability initiatives with human-in-the-loop evaluation