Multilingual Audio Evaluator
Creative & MediaArgentina - Fully RemoteFull-timePosted Oct 12
Help shape the future of AI by evaluating how conversational AI agents communicate and perform across different languages.
- Location: Remote / Global, subject to project location restrictions
- Type: Independent contractor / Project-based
- Commitment: To be confirmed
- Compensation: To be confirmed
- Project duration: 2–3 months
About the role
At Anyone AI, we create high-quality training and evaluation data for frontier AI models.
We’re looking for multilingual audio evaluators with strong spoken-language proficiency and technical literacy to assess conversational AI agents.
In this role, you’ll participate in live, real-time roleplay scenarios, capture session recordings and technical logs, label conversation transcripts, and evaluate interactions using structured rubrics. Your feedback will help improve the quality and reliability of AI conversations across languages.
What you’ll do
- Prepare and confirm the required tools and access before each live session.
- Conduct live, real-time roleplay scenarios with conversational AI agents.
- Capture recordings, session IDs, and tool-call or console logs.
- Label conversation transcripts according to project guidelines.
- Score interactions against structured evaluation rubrics.
- Provide clear written explanations supporting your scores.
- Read, validate, and troubleshoot JSON, identifying structural and formatting issues.
