Adebola Emiola

In my remote project-based work, I review AI-generated responses and data items against project-specific guidelines, checking relevance, accuracy, clarity, and consistency. I also annotate and label data, compare model responses, and provide feedback or rationales when task instructions require them.

I use structured rubrics to flag ambiguous cases and support consistent decisions across evaluation workflows. My two years of customer service experience included listening to customer concerns, clarifying needs, and helping resolve issues; I’m interested in evaluating conversational audio agents for real-world customer support.