Evaluate AI-generated media remotely through live voice conversations, image comparisons, and video reviews on a flexible schedule. Strong English communication and attention to detail are central.

Outlier seeks fluent English speakers to assess how well AI outputs follow prompts and sound or look natural. You will review voice, image, video, and audio outputs while writing evidence-based explanations. The work is performed remotely, with hours arranged around your schedule.

Key Responsibilities:

- Hold scenario-based conversations with English AI voice models
- Rank voice exchanges for naturalness, usefulness, and clarity
- Compare generated image and video pairs against prompts
- Identify distorted anatomy, flickering, text, motion, and audio issues
- Write specific explanations supporting ratings across evaluation dimensions

Requirements:

- Fluent English speaking and strong written communication
- Strong attention to detail during close reviews
- Comfort with natural, everyday conversational speech
- Experience writing short, evidence-based explanations or reviews
- Ability to decide clearly when both options have flaws

Bring careful listening, visual judgment, and accurate English writing to Outlier’s remote generative AI evaluation work.

📌 Generative AI Media Evaluator (Montreal)
🏢 Outlier
📍 Montreal