About this role
Role Overview
Help improve the safety of advanced AI systems by applying Hindi language fluency and cultural judgment to how models respond to sensitive topics. This role focuses on evaluating and strengthening Hindi-language interactions; prior AI or machine learning experience is not required, and training on the workflow is provided.
Key Responsibilities
- Create expert-level Hindi prompts covering a range of sensitive subject areas.
- Use structured guidelines to classify prompts and conversations.
- Identify adversarial wording and escalation patterns, then document the reasoning behind each assessment.
- Evaluate and improve how AI models handle sensitive topics in Hindi.
Qualifications
- Native or near-native Hindi fluency and business-level written English.
- A completed or in-progress bachelor’s degree.
- Strong written reasoning skills and close attention to detail.
- Sound judgment when working with sensitive and dual-use information.
Preferred Background
- Experience reviewing, grading, or red-teaming written or technical content.
- Experience in trust and safety, content moderation, policy evaluation, or adversarial testing.
Work Terms
- Remote, hourly engagement.
- Immediate start.
- Applicants in India or elsewhere in South Asia are preferred, though candidates based in other locations are welcome.
Compensation
$18 to $22 per hour.