AI Safety Red-Teamer — Bilingual English & Thai
Paid remote expert bounty in Expert network (Global). Work in the software you already know; rates and ladder published up front.
- $30-$250
- per hr, published up front
- 1
- slots left of 1
- Remote
- no AI experience required
What you'll be paid to show
About the role
We're building a specialized red team of bilingual language experts to stress-test AI models before they reach the public. The safest AI systems are the ones that have already been attacked — by us, first. As an AI Safety Expert working in English and Thai, you'll probe language models with adversarial prompts, surface hidden vulnerabilities, and generate the structured red-team data that makes these systems measurably safer.
This is fully remote, text-based work suited for detail-oriented linguists, researchers, or safety-minded thinkers who are comfortable engaging critically with sensitive and challenging content.
What you'll do
- Design and execute adversarial prompts intended to surface model weaknesses, biases, or unsafe behaviors
- Review and evaluate AI-generated outputs in both English and Thai for accuracy, safety, and cultural nuance
- Identify and document instances of misinformation, bias, harmful content, or policy violations
- Translate and localize red-teaming scenarios to ensure cultural and linguistic relevance in Thai-language contexts
- Provide structured written feedback and severity ratings on model failures
- Collaborate with a distributed team of safety researchers to refine red-teaming methodologies
- Maintain rigorous documentation standards for all flagged issues and edge cases
Requirements
- Native or near-native fluency in both English and Thai (written and spoken)
- Strong critical thinking and analytical skills, with comfort engaging with sensitive or uncomfortable subject matter
- Excellent written communication and documentation habits
- Ability to work independently in a fully remote, asynchronous environment
- Familiarity with AI/LLM concepts, prompt engineering, or content moderation is a plus
- Prior experience in linguistics, translation, content review, trust & safety, or research is a plus
- Reliable internet connection and availability for consistent contract hours
Compensation
Hourly rate: $24–$35/hour, based on experience and evaluation performance. Fully remote, flexible scheduling within project deadlines.
What we're looking for
- AI red-teaming
- Bilingual translation (English/Thai)
- Content moderation
- Bias and misinformation detection
- Adversarial prompt design
- AI safety evaluation
- Written documentation