AI Content Safety Evaluator

@ Taskify

About the AI Content Safety Evaluator Role

Taskify believes that AI safety starts with high-quality human data. We are building a flexible team of Safety Specialists to annotate and evaluate AI-generated content, ensuring outputs are safe, fair, and aligned with human values.

What You’ll Do

• Annotate AI-generated content for safety criteria such as bias, misinformation, disallowed content, and unsafe reasoning.
• Apply harm taxonomies and guidelines consistently.
• Document decision-making processes to improve annotation guidelines.
• Collaborate with researchers and engineers to enhance AI safety research and model development.

Who You Are

You are experienced in model evaluation, structured annotation, or applied research, and skilled at spotting subtle biases and inconsistencies. You must be comfortable in a fast-paced, evolving environment and capable of clearly explaining and defending your judgments.

Additional Information

• Role may involve reviewing sensitive content with support and clear guidelines.
• Work is text-based, remote, and flexible; suitable for both full-time and part-time contributors.
• Preferred candidates operate within US time zones; open to applicants from US, UK, and Canada.

Why Join Taskify?

Work on the cutting edge of AI safety and gain experience in a rapidly expanding, impactful field. Collaborate with experts across law, research, engineering, and creative fields to shape future AI systems.

Key Skills/Competency

• AI safety
• Data annotation
• Model evaluation
• Bias detection
• Misinformation
• Research collaboration
• Guideline adherence
• Structured analysis
• Decision documentation
• Remote work