AI Safety Red Team Expert at Mercor

AI Safety Red Team Expert (English & Dutch) | $48–$62/hr | Worldwide Remote

Mercor is assembling a team of adversarial AI safety experts to probe, stress-test, and red team conversational AI models. This contractor role is ideal for professionals with a background in AI adversarial research, cybersecurity, or socio-technical risk analysis who are fluent in both English and Dutch.

What You'll Do

• Red team conversational AI models and agents using jailbreaks, prompt injections, misuse cases, bias exploitation, and multi-turn manipulation techniques
• Generate high-quality human data by annotating failures, classifying vulnerabilities, and flagging systemic risks
• Apply structured frameworks, taxonomies, and benchmarks to ensure consistent and reproducible testing
• Produce clear reports, datasets, and attack case documentation that customers can act on

Who You Are

• Experienced in red teaming, AI adversarial work, cybersecurity, or socio-technical probing
• Naturally curious and adversarial — you instinctively push systems to their breaking points
• Structured in your approach, using established frameworks rather than ad hoc methods
• A clear communicator who can convey risks to both technical and non-technical audiences
• Adaptable and comfortable moving across diverse projects and customer environments

Nice-to-Have Specialties

• Adversarial ML: Jailbreak datasets, prompt injection, RLHF/DPO attacks, model extraction
• Cybersecurity: Penetration testing, exploit development, reverse engineering
• Socio-technical risk: Harassment/disinfo probing, abuse analysis, conversational AI testing
• Creative probing: Psychology, acting, or writing skills applied to unconventional adversarial thinking

What Success Looks Like

• You uncover vulnerabilities that automated tests miss
• You deliver reproducible artifacts that strengthen customer AI systems
• Evaluation coverage expands with more scenarios tested and fewer production surprises
• Mercor customers trust their AI safety because you've already probed it like an adversary

Important Notes

This role involves reviewing AI outputs related to sensitive topics such as bias, misinformation, and harmful behaviors. All work is text-based. Participation in higher-sensitivity projects is optional and supported by clear guidelines and wellness resources. Topics will always be communicated in advance.

Language Requirement: Native fluency in both English and Dutch is required.