Muhamad Ihsan P.

I specialize in conversational AI evaluation, AI quality assurance, human evaluation auditing, and data annotation for machine learning projects. My experience includes: • Live speech-to-speech AI evaluation • Side-by-side and pairwise model comparison • Human evaluation auditing and quality review • Audio and text evaluation • Data annotation and validation • Error identification and guideline compliance • Multilingual AI evaluation in Indonesian and English I am experienced in applying detailed evaluation guidelines and quality taxonomies to assess naturalness, engagement, utility, audio quality, instruction following, factual accuracy, task success, and conversational dynamics. I also have experience working in high-volume annotation environments while maintaining strong accuracy and consistency. Native Indonesian speaker with professional working proficiency in English.