AI Summary
Join Mercor as a Red Team Data Expert to connect elite creative and technical talent with leading AI research labs. Conduct jailbreaks, prompt injections, and bias exploitation to improve AI model performance. Work independently and asynchronously, with flexible hours.
Key Highlights
Conduct red teaming activities
Improve AI model performance
Work independently and asynchronously
Technical Skills Required
Benefits & Perks
$32/hour compensation
Remote work
Flexible hours
Job Description
About The Job
Mercor connects elite creative and technical talent with leading AI research labs. Headquartered in San Francisco, our investors include Benchmark, General Catalyst, Peter Thiel, Adam D'Angelo, Larry Summers, and Jack Dorsey.
Position: Red Team Data Expert
Type: Full-time or Part-time Contract Work
Compensation: $32/hour
Location: Remote; Geography restricted to USA, Egypt, Saudi Arabia, UAE
Role Responsibilities
- Red team conversational AI models and agents. Conduct jailbreaks, prompt injections, misuse cases, bias exploitation, and multi-turn manipulation.
- Generate high-quality human data. Annotate failures, classify vulnerabilities, and flag systemic risks.
- Apply structure. Follow taxonomies, benchmarks, and playbooks to keep testing consistent.
- Document reproducibly. Produce reports, datasets, and attack cases customers can act on.
- Work independently and asynchronously. Ensure flexible hours while improving AI model performance.
Must-Have
- Fluent in English & Arabic. Native-level fluency required.
- Prior red teaming experience in AI adversarial work, cybersecurity, or socio-technical probing.
- Strong communication skills. Explain risks clearly to technical and non-technical stakeholders.
- Adaptable. Thrive on moving across projects and customers.
- Experience in Adversarial ML: jailbreak datasets, prompt injection, RLHF/DPO attacks, model extraction.
- Background in Cybersecurity: penetration testing, exploit development, reverse engineering.
- Expertise in socio-technical risk: harassment/disinfo probing, abuse analysis, conversational AI testing.
- Creative probing skills: psychology, acting, writing for unconventional adversarial thinking.
- Hourly contractor
- Upload resume
- AI interview based on your resume
- Submit form
- For details about the interview process and platform information, please check: https://talent.docs.mercor.com/welcome/welcome
- For any help or support, reach out to: support@mercor.com
,