AI-Generated Content Evaluator for Study Tools
Text
Built, evaluated, and improved AI-generated quiz and study content for psychology learning applications. Responsible for assessing AI outputs for accuracy, clinical safety, and appropriateness in sensitive mental health contexts. Utilized domain expertise to ensure the labeled data reflected nuanced understanding of counseling psychology and ethical practice.
• Leveraged Groq API (Llama 3.3 70B) to generate and review AI content.
• Focused on high-stakes scenarios within psychological assessment and exam simulation.
• Labeled and rated multilingual data leveraging knowledge in English, Swahili, Arabic, Hebrew, and Russian.
• Conducted ongoing review and correction cycles as part of iterative tool development.
Built, evaluated, and improved AI-generated quiz and study content for psychology learning applications. Responsible for assessing AI outputs for accuracy, clinical safety, and appropriateness in sensitive mental health contexts. Utilized domain expertise to ensure the labeled data reflected nuanced understanding of counseling psychology and ethical practice. • Leveraged Groq API (Llama 3.3 70B) to generate and review AI content. • Focused on high-stakes scenarios within psychological assessment and exam simulation. • Labeled and rated multilingual data leveraging knowledge in English, Swahili, Arabic, Hebrew, and Russian. • Conducted ongoing review and correction cycles as part of iterative tool development.
2024 - 2025