AI Summary
Mercor seeks an AI Red-Teamer to red-team AI models and agents through jailbreaks, prompt injections, and misuse cases. The ideal candidate has prior red-teaming experience in AI adversarial work, cybersecurity, or socio-technical probing. Strong communication skills are required to explain risks to technical and non-technical stakeholders.
Key Highlights
Red-team AI models and agents
Prior red-teaming experience in AI adversarial work
Strong communication skills
Key Responsibilities
Red-team AI models and agents through jailbreaks, prompt injections, misuse cases, and exploits
Generate high-quality human data by annotating failures, classifying vulnerabilities, and flagging systemic risks
Apply structure by following taxonomies, benchmarks, and playbooks to ensure consistent testing
Technical Skills Required
Benefits & Perks
$50-$111/hour
Remote-friendly (US time zones)
Geography restricted to US, UK, Canada
Nice to Have
Experience with Adversarial ML, including jailbreak datasets, prompt injection, RLHF/DPO attacks, and model extraction
Cybersecurity skills in penetration testing, exploit development, and reverse engineering
Understanding of socio-technical risk, including harassment/disinfo probing and abuse analysis
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: AI Red-Teamer
Type: Full-time or Part-time
Compensation: $50–$111/hour
Location: Remote-friendly (US time zones); Geography restricted to US, UK, Canada
Role Responsibilities
- Red-team AI models and agents through jailbreaks, prompt injections, misuse cases, and exploits.
- Generate high-quality human data by annotating failures, classifying vulnerabilities, and flagging systemic risks.
- Apply structure by following taxonomies, benchmarks, and playbooks to ensure consistent testing.
- Document reproducibly to produce reports, datasets, and attack cases that customers can act on.
- Flex across projects to support different customers, from LLM jailbreaks to socio-technical abuse testing.
Must-Have
Interested in remote work opportunities in Cyber Security? Discover Cyber Security Remote Jobs featuring exclusive positions from top companies that offer flexible work arrangements.
- Prior red-teaming experience in AI adversarial work, cybersecurity, or socio-technical probing.
- Curiosity and adversarial instinct to push systems to breaking points.
- Structured approach using frameworks or benchmarks.
- Strong communication skills to explain risks to technical and non-technical stakeholders.
- Adaptability to thrive across various projects and customers.
- Experience with Adversarial ML, including jailbreak datasets, prompt injection, RLHF/DPO attacks, and model extraction.
- Cybersecurity skills in penetration testing, exploit development, and reverse engineering.
- Understanding of socio-technical risk, including harassment/disinfo probing and abuse analysis.
- Creative probing skills in psychology, acting, or writing for unconventional adversarial thinking.
Browse our curated collection of remote jobs across all categories and industries, featuring positions from top companies worldwide.
- Hourly contractor
- Compensation varies by project, customer, and content category.
- 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
,
Similar Jobs
Explore other opportunities that match your interests
Visa Sponsorship
Relocation
Remote
Job Type
Full-time
Experience Level
Mid-Senior level
remotehunter
United State
Visa Sponsorship
Relocation
Remote
Job Type
Full-time
Experience Level
Mid-Senior level
remotehunter
United State
Visa Sponsorship
Relocation
Remote
Job Type
Internship
Experience Level
Internship
voltus
United State