Welo Global
Andromeda Sadiradra - Audio Rater - Generalist - English (United State)
About this role
Overview
We're looking for detail-oriented Audio Raters to evaluate conversations between users and AI voice agents. You'll listen to recorded interactions and assess the quality of the AI agent's responses across two key dimensions.
Project Details
Start Date: ASAP
Duration: 10 hours/week
Job Type: Freelance
Location: Remote (United States)
Language: English
Pay Rate: $26.33/hour
Responsibilities
- Listen carefully to recorded conversations between a person and an AI voice agent
- Rate each of the agent's turns on two independent 1–5 scales:
- Content – Was the response helpful, relevant, and appropriate?
- Prosody – Did the voice sound natural, well-paced, and expressive?
- Write a short, specific, and clear justification for each score given
What We're Looking For:
- Strong listening and attention-to-detail skills
- Ability to give consistent, well-reasoned ratings
- Clear, concise written communication
- Reliable availability for ~10 hours/week
Thank you for your interest in joining Welo Data’s community and contributing to this exciting project. We look forward to collaborating with you!
#L1-CC1
Written by Welo Global. Original job post
Opens the application — the Jobs AI extension fills it for you. Set up autofill
Opens the official application on the employer’s site. No login required.
Welo Global
Welo Global develops LLM-based autoraters and manages the technical transition of templates to leverage large language models for evaluation tasks. The company is hiring Prompt Engineers to optimize model performance through prompt engineering and internal tooling.
- Industry
- Technology & Software
Preparing likely interview questions for this role…