About this role
Role Overview
Help improve how advanced AI models respond to sensitive topics in Croatian. You will use Croatian language fluency and cultural judgment to evaluate model interactions, identify safety concerns, and support stronger handling of sensitive and dual-use information. No prior AI or machine learning experience is required, and training on the workflow will be provided.
Key Responsibilities
- Create expert-level Croatian prompts across a range of sensitive subject areas.
- Apply structured guidelines to classify prompts and conversations.
- Identify adversarial wording and escalation patterns, and document the reasoning behind your decisions.
- Evaluate and strengthen AI model handling of sensitive topics in Croatian.
Qualifications
- Native or near-native Croatian fluency and business-level written English.
- Bachelor''s degree completed or currently in progress.
- Strong written reasoning skills and close attention to detail.
- Sound judgment when working with sensitive and dual-use information.
Preferred Qualifications
- Based in Croatia or elsewhere in Eastern Europe, though applicants located outside the region are welcome.
- 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.
- Eastern Europe location is preferred but not required.
Compensation
- $38 to $42 per hour.