AI Summary
Mercor is seeking a Red Team Specialist to connect elite creative and technical talent with leading AI research labs. The role involves red teaming conversational AI models and agents to identify jailbreaks, prompt injections, and misuse cases. Key requirements include native-level fluency in English and Japanese, prior experience in red teaming, and strong communication skills.
Key Highlights
Red team conversational AI models and agents
Identify jailbreaks, prompt injections, and misuse cases
Generate high-quality human data by annotating failures
Key Responsibilities
Red team conversational AI models and agents
Generate high-quality human data by annotating failures
Apply structure by following taxonomies, benchmarks, and playbooks
Technical Skills Required
Benefits & Perks
$50/hour
Remote work
Flexible work arrangement
Nice to Have
Adversarial ML: jailbreak datasets, prompt injection, RLHF/DPO attacks
Background in Cybersecurity: penetration testing, exploit development, reverse engineering
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 Specialist
Type: Full-time or Part-time Contract Work
Compensation: $50/hour
Location: Remote; Geography restricted to USA, Japan
Role Responsibilities
- Red team conversational AI models and agents to identify jailbreaks, prompt injections, and misuse cases.
- 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 by producing reports, datasets, and attack cases for customer action.
- Work independently and asynchronously to meet deadlines while enhancing AI model safety.
Interested in remote work opportunities in QA & Testing? Discover QA & Testing Remote Jobs featuring exclusive positions from top companies that offer flexible work arrangements.
- Native-level fluency in English and Japanese.
- Prior experience in red teaming (AI adversarial work, cybersecurity, socio-technical probing).
- Strong communication skills to explain risks to technical and non-technical stakeholders.
- Ability to adapt and thrive across diverse 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.
Browse our curated collection of remote jobs across all categories and industries, featuring positions from top companies worldwide.
- Hourly contractor, Paid weekly via Stripe Connect.
- 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
Not Applicable
Radformation
United State
Visa Sponsorship
Relocation
Remote
Job Type
Contract
Experience Level
Mid-Senior level
hatch pros
United State
Software Test Engineer
••••••
••••••
••••••
Job Type
••••••
Experience Level
••••••
Paylocity
United State