Evaluate AI-generated media remotely on your own schedule using fluent English, careful observation, and evidence-based judgment. Review voices, images, and videos for quality.

Outlier, owned and operated by Scale AI, seeks detail-oriented English speakers for AI evaluation projects. You will assess generated media, explain issues in writing, and help improve advanced AI systems. The work includes conversational voice testing, visual comparisons, caption labeling, and audio review.

Key Responsibilities:

- Conduct live English conversations with AI voice models
- Compare generated images and videos against prompts
- Inspect outputs for visual, motion, text, and audio issues
- Rate adherence, quality, realism, and naturalness
- Write specific explanations based on observed evidence

Requirements:

- Fluent English and transparent written communication
- Strong attention to detail and patience
- Comfort with natural conversational speech
- Experience writing short evidence-based reviews
- Ability to decide when both options have flaws

Apply your English communication and media evaluation skills to help Outlier improve AI-generated voices, images, and videos.

#J-18808-Ljbffr

📌 AI Media Evaluation Specialist (London)
🏢 SCALE AI
📍 London