AI Safety Red Team Expert – English and Finnish, United States Remote
Conduct adversarial testing of conversational AI models and agents for Mercor’s human-data AI projects. Create reproducible vulnerability data to help strengthen frontier AI systems.
Description
- Test conversational AI models and agents using jailbreaks, prompt injections, misuse scenarios, bias exploitation, and multi-turn manipulation
- Annotate failures, categorize vulnerabilities, and identify systemic risks
- Apply established taxonomies, benchmarks, and playbooks for consistent evaluations
- Create reproducible reports, datasets, and attack cases for customers
- Identify vulnerabilities that automated testing may overlook
- Broaden evaluation coverage and help reduce unexpected production issues
- Work with leading researchers on projects that train and improve AI systems
Requirements
- Fluent or native English and Finnish language skills
- Previous red teaming experience in AI adversarial work, cybersecurity, or socio-technical probing
- Ability to test AI systems adversarially and push them toward failure points
- Experience applying frameworks or benchmarks for structured testing
- Ability to communicate risks clearly to technical and non-technical audiences
- Adaptability across projects and customer requirements
- Availability for an independent contractor engagement
- Must not be an H-1B or STEM OPT candidate
- Preferred: adversarial machine learning experience, including jailbreak datasets, prompt injection, RLHF/DPO attacks, or model extraction
- Preferred: cybersecurity experience in penetration testing, exploit development, or reverse engineering
- Preferred: socio-technical risk experience in harassment or disinformation probing, abuse analysis, or conversational AI testing
- Preferred: psychology, acting, or writing experience that supports unconventional adversarial thinking
Benefits
- Fully remote work
- Flexible scheduling
- Weekly payments through Stripe or Wise
- Wellness resources and clear guidelines for higher-sensitivity projects
- Opportunity to gain experience in human-data AI red teaming
- Direct opportunity to help make AI systems more robust, safe, and trustworthy
- Competitive pay
- Referral bonus of up to $250 for each successful referral