AI Safety Expert for English and Vietnamese Red Teaming

Join a red team of human data experts who probe conversational AI models with adversarial inputs to surface vulnerabilities and produce high-quality red team data that improves model safety. This text-based role focuses on reviewing AI outputs that touch on sensitive topics such as bias, misinformation, or harmful behaviors. Participation in higher-sensitivity assignments is optional, topics will be communicated before exposure, and clear guidelines and wellness resources are provided.

• Red team conversational AI models and agents, including jailbreaks, prompt injection, misuse cases, bias exploitation, and multi-turn manipulation
• Generate high-quality human data by annotating failures, classifying vulnerabilities, and flagging systemic risks
• Apply structure and consistency by following taxonomies, benchmarks, and playbooks during testing
• Document findings reproducibly, producing reports, datasets, and attack cases that customers can act on
• Review model outputs that touch on sensitive topics, with optional participation in higher-sensitivity projects governed by explicit guidelines

• Native fluency in both English and Vietnamese is required
• Prior red teaming experience, such as AI adversarial work, cybersecurity, or socio-technical probing
• Curious and adversarial mindset, with an instinct to push systems to breaking points
• Structured approach to testing, using frameworks, benchmarks, or playbooks rather than ad hoc methods
• Strong communication skills, able to explain risks clearly to technical and non-technical stakeholders
• Adaptable, comfortable moving across projects and customer contexts

• Adversarial ML, including jailbreak datasets, prompt injection, RLHF or DPO related attacks, and model extraction
• Cybersecurity experience such as penetration testing, exploit development, or reverse engineering
• Socio-technical risk analysis, for example harassment, disinformation probing, abuse analysis, or conversational AI testing
• Creative probing skills such as psychology, acting, or writing for unconventional adversarial approaches

• Uncovering vulnerabilities that automated tests miss
• Delivering reproducible artifacts that help customers strengthen their AI systems
• Expanding evaluation coverage so more scenarios are tested and fewer surprises occur in production
• Customers trusting the safety of their AI because it has been thoroughly probed by the red team

• Gain hands-on experience in human data driven AI red teaming at the frontier of safety testing
• Play a direct role in making AI systems more robust, safe, and trustworthy

Remote, hourly engagement. All assignments are text-based. Participation in higher-sensitivity work is optional and supported by guidelines and wellness resources. Topics that may be sensitive will be communicated before exposure.

17 - 25 hourly

• Native fluency in English and Vietnamese is required
• Remote work is allowed