Bilingual Portuguese AI Safety Evaluator [Remote]

Role Overview

Help improve the safety of advanced AI models by applying Portuguese language fluency and cultural judgment to evaluate how they respond to sensitive topics. Training on the workflow is provided, and prior AI or machine learning experience is not required.

Key Responsibilities

• Write expert-level Portuguese prompts covering a range of sensitive subject areas.
• Use structured guidelines to classify prompts and conversations.
• Identify adversarial phrasing and escalation patterns, then document the reasoning behind each judgment.
• Evaluate and strengthen AI model handling of sensitive Portuguese-language content.

Qualifications

• Native or near-native Portuguese 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 Portugal or elsewhere in Western Europe, though applicants in other locations are welcome.
• Experience reviewing, grading, or red-teaming written or technical content.
• Background in trust and safety, content moderation, policy evaluation, or adversarial testing.

Work Terms

• Remote, hourly engagement.
• Immediate start.

Compensation

• 40 to 44 per hour.