AI Safety Red Teamer — English & Indonesian Bilingual Specialist

About the role

We're building a global red team of human data experts dedicated to making AI systems safer before they reach the public. This is not a typical QA or content moderation job — you'll be actively probing AI models with adversarial prompts, surfacing hidden vulnerabilities, and generating the structured red-team data that helps our AI systems detect and resist harmful, biased, or misleading outputs.

We're specifically looking for bilingual specialists fluent in **English and Indonesian** who can evaluate model behavior across both languages and cultural contexts, ensuring safety coverage isn't limited to English-only use cases.

What you'll do

• Design and execute adversarial prompts intended to expose weaknesses in AI model outputs
• Review and annotate AI responses for bias, misinformation, harmful behavior, and policy violations
• Evaluate model outputs in both English and Indonesian, flagging language- or culture-specific failure modes
• Document vulnerabilities with clear, structured write-ups that feed directly into model safety improvements
• Collaborate with a distributed team of reviewers to calibrate standards and maintain consistent evaluation quality
• Provide feedback on edge cases involving sensitive topics such as misinformation, discrimination, and unsafe instructions
• Iterate on red-teaming strategies as models evolve and new failure patterns emerge

Requirements

• Native or near-native fluency in **both English and Indonesian** (written and spoken)
• Strong analytical and critical thinking skills, with attention to nuance and context
• Comfort engaging with sensitive, controversial, or potentially disturbing content in a professional, objective manner
• Excellent written communication skills for documenting findings clearly
• Reliable access to a computer and stable internet connection for remote work
• Prior experience in content moderation, linguistics, trust & safety, AI training data, or related fields is a plus
• Ability to work independently while following detailed evaluation guidelines

Compensation

This role is paid hourly, in the range of $17–$25/hour depending on experience and evaluation throughput. Work is fully remote and flexible, with opportunities for ongoing engagement as the project scales.