Freelance Clinical AI Evaluator (Independent Contractor)
TextRLHF
I contributed nursing domain expertise to AI training projects involving clinical text evaluation and prompt engineering. My responsibilities included writing detailed prompts, evaluating AI-generated responses for clinical accuracy, and identifying model failure modes. I used structured rubrics to rate responses and provided detailed written justifications for all decisions.
• Developed multi-step nursing scenarios for use as model prompts.
• Evaluated AI responses for logical soundness and adherence to professional standards.
• Identified and documented unsafe model outputs and gaps in reasoning.
• Collaborated in refining evaluation metrics and improving AI system safety.
I contributed nursing domain expertise to AI training projects involving clinical text evaluation and prompt engineering. My responsibilities included writing detailed prompts, evaluating AI-generated responses for clinical accuracy, and identifying model failure modes. I used structured rubrics to rate responses and provided detailed written justifications for all decisions. • Developed multi-step nursing scenarios for use as model prompts. • Evaluated AI responses for logical soundness and adherence to professional standards. • Identified and documented unsafe model outputs and gaps in reasoning. • Collaborated in refining evaluation metrics and improving AI system safety.
2026 - Present