AI Red-Teamer (English & Portuguese)
Job Description
As AI systems are deployed globally, their safety and ethical alignment in diverse linguistic and cultural contexts become paramount. Your expertise in Portuguese (both European and Brazilian variants) and English will be crucial in stress-testing AI models, uncovering subtle biases, and preventing harmful outputs that could impact user trust and cultural integrity. This role is at the forefront of responsible AI development.
Key Responsibilities
Design and execute sophisticated adversarial prompts and test cases to expose safety gaps in AI models, specifically targeting Portuguese-English bilingual interactions.
Identify and categorize instances of cultural insensitivity, political bias, misinformation, or harmful content generated by AI in both languages, considering the specific nuances of Portuguese-speaking cultures.
Provide comprehensive, actionable feedback and detailed reports on identified vulnerabilities, including linguistic and cultural context.
Contribute to the development of robust red-teaming frameworks tailored for Portuguese linguistic and cultural specificities.
Analyze model responses for nuanced semantic errors, pragmatic failures, and potential for misuse across various Portuguese dialects and English.
Ideal Qualifications
Native or near-native fluency in Portuguese (both European and Brazilian Portuguese preferred) and English, with profound cultural awareness.
Proven experience in quality assurance, linguistic validation, or security testing, ideally with AI/ML systems.
Strong analytical skills to dissect complex AI outputs and identify subtle biases or safety risks.
Familiarity with common adversarial attack techniques against LLMs (e.g., prompt injection, data poisoning).
Ability to work independently and meticulously document findings in a structured manner.
Background in computational linguistics, Lusophone studies, or information security is a significant asset.
Project Timeline
Start Date: As soon as possible
Duration: 6 months, with potential for extension
Commitment: Part-time, 20-30 hours per week
Help us build safe, ethical, and culturally intelligent AI for a global audience!