AI Medical Trainer
TextPrompt Response Writing SFT
Designed and optimized medical prompts to train and evaluate large language models in clinical settings. Conducted systematic rubric-based evaluation to assess the quality and accuracy of AI outputs. Provided structured feedback for model refinement to improve clinical reasoning and safety.
• Developed medical Q&A tasks and prompt engineering for AI
• Identified errors, inconsistencies, and edge cases in AI model responses
• Ensured high-quality data annotation and medical content validation
• Supported AI alignment with medical standards in model evaluation.
Designed and optimized medical prompts to train and evaluate large language models in clinical settings. Conducted systematic rubric-based evaluation to assess the quality and accuracy of AI outputs. Provided structured feedback for model refinement to improve clinical reasoning and safety. • Developed medical Q&A tasks and prompt engineering for AI • Identified errors, inconsistencies, and edge cases in AI model responses • Ensured high-quality data annotation and medical content validation • Supported AI alignment with medical standards in model evaluation.
2025 - 2025