AI Safety Experts – English, Thai

This is a fully remote position, open to applicants in United States.

📋 Description

• Conduct red team assessments on conversational AI models and agents through methods such as jailbreaks, prompt injections, misuse scenarios, bias exploitation, and multi-turn manipulations.

• Generate human data by annotating failures, categorizing vulnerabilities, and identifying systemic risks.

• Implement taxonomies, benchmarks, and playbooks to ensure consistency in testing.

• Create reproducible reports, datasets, and attack scenarios that customers can utilize.

• Discover vulnerabilities that automated tests often overlook.

• Broaden evaluation coverage to minimize unforeseen issues in production.

• Enhance customer AI systems and foster trust in their safety.

• Collaborate across various projects and clients for Mercor, which partners with AI labs and businesses to develop cutting-edge models.

⛳️ Requirements

• Previous experience in red teaming focused on AI adversarial tasks, cybersecurity, or socio-technical probing.

• Fluent in both English and Thai.

• Familiarity with jailbreaks, prompt injections, misuse cases, bias exploitation, or multi-turn manipulations.

• Capability to probe systems adversarially and challenge them to their limits.

• Proficiency in utilizing frameworks or benchmarks instead of employing random hacks.

• Ability to clearly articulate risks to both technical and non-technical audiences.

• Adaptability across various projects and clients.

• Preferred areas of expertise include adversarial machine learning, cybersecurity, socio-technical risks, or innovative probing techniques.

• Knowledge in adversarial ML, including jailbreak datasets, prompt injection, RLHF/DPO attacks, or model extraction is advantageous.

• Understanding of cybersecurity concepts such as penetration testing, exploit development, or reverse engineering is a plus.

• Experience in socio-technical risk areas like harassment/disinformation probing, abuse analysis, or testing of conversational AI is beneficial.

• Background in creative probing through psychology, acting, or writing is an additional asset.

• Must be eligible to work without H1-B or STEM OPT support.

🏝️ Benefits

• Fully remote position.

• Flexible working hours allowing you to set your own schedule.

• Weekly payments through Stripe or Wise.

• Participation in higher-sensitivity projects is optional.

• Clear guidelines and wellness resources available for projects involving sensitive content.

• Opportunity to gain experience in human data-driven AI red teaming.

• Contribute to enhancing the robustness, safety, and trustworthiness of AI systems.

• Collaborate with top-tier researchers.

• Competitive compensation.

• Reasonable accommodations available upon request.