Software Engineer
Outlier
About the Role
Outlier is looking for talented, detail-oriented English speakers to help train generative AI voice, image, and video models. This is a freelance, remote opportunity with flexible hours.
Key Responsibilities
- Hold live, scenario-based conversations in English with AI voice models, then rank them based on naturalness, usefulness, and clarity.
- Compare pairs of AI-generated images and videos, judging which better follows the prompt.
- Inspect outputs closely, including zooming and replaying, to spot problems such as distorted anatomy, flickering or unnatural motion, text errors, and audio mismatches.
- Rate outputs across dimensions like adherence, quality, and realism.
- Write specific explanations in English pointing to observed issues or strengths.
Requirements & Tech Stack
- A computer with a reliable internet connection.
- Headphones.
- A quiet place to talk for projects involving live conversation.
- Your ratings and written explanations must be your own work; AI tools cannot be used to write them.
- Getting started includes a short screening and onboarding, which may include a brief spoken English check.
Qualifications
- Fluent English speaker with strong, clear written communication.
- Comfortable with natural, everyday conversational speech.
- Pursuing or holding a Bachelor's degree or above.
- Strong attention to detail, with patience to look and listen closely.
- Experience writing short, evidence-based explanations or reviews.
Payment
- Project work: Earn up to USD $7.5 per hour for core project work.

