Remote AI Safety Evaluator — Project-Based Feedback

Mercor; New York (NY); Remote; USD 21.000 - 34.000; Vollzeit

Zusammenfassung

Mercor is seeking contributors to review short English-language conversations and evaluate how well AI responses address user requests. You will follow a set of guidelines to assess each conversation and submit structured feedback.

This is a remote, project-based role with training provided. Strong English reading comprehension and attention to detail are important, and prior annotation experience is a plus. You will work in flexible batches and report findings to the project team.

Qualifikationen

• Strong English reading comprehension.
• Good attention to detail and ability to follow written instructions.
• Prior review or annotation experience is helpful, but not required.

Aufgaben

• Read user prompts and AI responses.
• Apply the appropriate labels using the project guidelines.
• Work independently and carefully across assigned batches.

Kenntnisse

Strong English reading comprehension

Attention to detail

Ability to follow instructions

Jobbeschreibung

Mercor is seeking contributors to review short English-language conversations and evaluate how well AI responses address user requests. You will follow a set of guidelines to assess each conversation and submit structured feedback.

This is a remote, project-based role with training provided. Strong English reading comprehension and attention to detail are important, and prior annotation experience is a plus. You will work in flexible batches and report findings to the project team.