Content Safety Expert

Role Description : Your primary goal will be to identify and analyze potential safety policy violations, such as Hate Speech, Harassment, Sexually Explicit Content, Dangerous and Harmful Acts, and Child Safety concerns. The detailed feedback and insights you provide will be instrumental in training, fine-tuning, and improving the safety guardrails of our models.

Key Responsibilities

• Multi-Modal Content Review : Systematically review and analyze AI-generated content (text, images, audio, video) to detect violations of our safety policies.
• Policy Application and Annotation : Apply a complex set of safety policies with high accuracy and consistency. Provide detailed labels and annotations that capture the nuance of potential harms.
• High-Quality Feedback Loop : Author detailed, data-driven feedback and rationale for your evaluations, which will be used directly by our engineering and research teams to improve model performance.
• Trend Identification : Proactively identify, analyze, and document emerging trends, loopholes, and adversarial attack vectors (e.g., new forms of hate speech, jailbreaking prompts) that challenge our safety systems.
• Policy Refinement : Contribute to the development and refinement of safety policies by providing expert feedback on policy clarity, edge cases, and operational feasibility.
• Calibration and Quality Assurance : Participate in regular calibration sessions with team members to ensure consistent and fair application of policies.

Required Qualifications (Must-Haves)

Preferred Qualifications (Nice-to-Haves)