AI Safety Expert for English and Thai Red Teaming

Perform adversarial testing of conversational AI by probing models with crafted inputs, surfacing vulnerabilities, and producing reproducible attack cases and human-labeled data that product and engineering teams can use to harden systems. This is text-based red teaming that can involve sensitive topics such as bias, misinformation, or harmful behaviors. Participation in higher-sensitivity reviews is optional and supported with clear guidelines and wellness resources, and topics will be communicated before exposure.

• Red team conversational AI models and agents, including jailbreaks, prompt injection, misuse cases, bias exploitation, and multi-turn manipulation
• Generate high-quality human data: annotate failures, classify vulnerabilities, and flag systemic risks
• Apply structure to testing by following taxonomies, benchmarks, and playbooks to maintain consistency
• Document findings reproducibly by producing reports, datasets, and attack cases that customers or teams can act on

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

• Adversarial machine learning, including jailbreak datasets, prompt injection, RLHF or DPO attack techniques, and model extraction
• Cybersecurity experience such as penetration testing, exploit development, or reverse engineering
• Socio-technical risk expertise, including harassment and disinformation probing, abuse analysis, and conversational AI testing
• Creative probing skills from psychology, acting, or creative writing to design unconventional adversarial inputs

• Discover vulnerabilities that automated tests miss
• Deliver reproducible artifacts that directly strengthen customer AI systems
• Expand evaluation coverage so more scenarios are tested and fewer surprises arise in production
• Increase customer trust in deployed AI by identifying and mitigating real-world attack vectors

• Remote engagement, all work is text-based
• Hourly employment
• Participation in higher-sensitivity projects is optional and accompanied by clear guidelines and wellness resources; topics will be disclosed before exposure

• $24.00 to $35.00 per hour

• Native fluency in both English and Thai is required
• Work is remote; candidates must be able to work remotely from their location