Senior Content Safety Evaluator
Image
As a Senior Content Safety Evaluator at SafeStream Digital, I analyzed a high volume of AI-generated images and text for policy compliance and safety. I reviewed and escalated harmful, abusive, or policy-violating content to improve AI model classification rules. I provided detailed documentation to enhance the moderation framework and support new evaluators.
• Maintained a 98.7% accuracy score during evaluation of 400+ images and text items daily.
• Escalated edge cases to refine model performance and reduce false positives/negatives.
• Produced weekly reports to identify and mitigate emerging harmful content patterns.
• Utilized internal/proprietary tooling and leading AI moderation APIs for comprehensive analysis.
As a Senior Content Safety Evaluator at SafeStream Digital, I analyzed a high volume of AI-generated images and text for policy compliance and safety. I reviewed and escalated harmful, abusive, or policy-violating content to improve AI model classification rules. I provided detailed documentation to enhance the moderation framework and support new evaluators. • Maintained a 98.7% accuracy score during evaluation of 400+ images and text items daily. • Escalated edge cases to refine model performance and reduce false positives/negatives. • Produced weekly reports to identify and mitigate emerging harmful content patterns. • Utilized internal/proprietary tooling and leading AI moderation APIs for comprehensive analysis.
2022 - Present