AI Evaluation Specialist - Remote, Flexible Hours

Outlier; Wilmington (NC); À distance; USD 12 000 - 21 000; Plein temps

Avantages offerts par ce poste

Flexible hours

Remote work

Weekly payments

LLM access

Résumé du poste

Outlier is seeking detail-oriented English speakers to review AI-generated media remotely. You will hold live conversations with AI voice models, compare image and video outputs, and explain what looked or sounded off in writing.

Earn up to $15 USD per hour with flexible hours and weekly payments. Contributors can work from home or while traveling, with access to leading LLMs and ongoing opportunities across projects.

Qualifications

• Fluent English with clear written communication.
• Excellent attention to detail and ability to replay or zoom in.
• Bachelor's degree or higher preferred.
• Comfortable explaining realistic scenarios in conversation.
• Experience writing concise evidence-based reviews.

Responsabilités

• Holding a live, scenario-based conversation in English with AI voice models, then ranking naturalness, usefulness, and clarity.
• Comparing pairs of AI-generated images and videos and judging which follows the prompt better.
• Inspecting outputs closely, including zooming in and replaying, to spot problems like distorted anatomy, flickering or unnatural motion, text errors, and audio-video mismatch.
• Rating each output across dimensions like adherence, quality, and realism, then writing a specific explanation in English.

Connaissances

Fluent English

Attention to detail

Clear written communication

Verbal reasoning

Formation

Bachelor's degree

Description du poste

Outlier is seeking detail-oriented English speakers to review AI-generated media remotely. You will hold live conversations with AI voice models, compare image and video outputs, and explain what looked or sounded off in writing.

Earn up to $15 USD per hour with flexible hours and weekly payments. Contributors can work from home or while traveling, with access to leading LLMs and ongoing opportunities across projects.