Work Type
Remote
Location
Global
Compensation
Not specified
About this opportunity
Overview
Anyone AI is looking for multilingual audio evaluators to help assess how conversational AI agents communicate and perform across languages. This is a remote, project-based independent contractor role with a project duration of 2–3 months. The location is listed as remote/global, subject to project location restrictions.
The work focuses on live evaluation sessions, transcript labeling, structured scoring, and detailed feedback that helps improve the quality and reliability of AI conversations.
What You’ll Do
- Prepare and confirm the required tools and access before each live session.
- Run live, real-time roleplay scenarios with conversational AI agents.
- Capture session recordings, session IDs, and tool-call or console logs.
- Label conversation transcripts according to project guidelines.
- Score interactions using structured evaluation rubrics.
- Provide clear written explanations that support your scores.
- Read, validate, and troubleshoot JSON, including structural and formatting issues.
Requirements
- C1/C2 spoken fluency in at least one of the target languages.
- Ability to demonstrate language proficiency through a speaking and listening assessment.
- Strong JSON skills, including reading, validation, troubleshooting, and identifying structural or formatting errors.
- Comfort using digital tools and collecting recordings and technical logs.
- Strong attention to detail and the ability to follow evaluation guidelines consistently.
- Clear written communication and sound judgment when assessing AI interactions.
Target Languages
- Welsh
- Dutch
- Greek
- Italian
- French
- German
- Portuguese
Nice to Have
- Experience in AI evaluation, audio annotation, or transcript labeling.
- Background in technical support, quality assurance, or software development.
- Familiarity with conversational AI, APIs, and structured data.
