AI Red-Teamer
Mercor
Job Overview
Who's the hiring manager?
Sign up to PitchMeAI to discover the hiring manager's details for this job. We will also write them an intro email for you.
Job Description
About Mercor
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.
As an AI Red-Teamer, you will play a crucial role in ensuring the safety and robustness of cutting-edge AI models.
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.
Qualifications
Must-Have
- 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.
Preferred
- 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.
Compensation & Legal
This is an hourly contractor position. Compensation varies by project, customer, and content category.
Application Process
The application process takes approximately 20–30 minutes to complete:
- Upload your resume.
- Complete an AI interview based on your resume.
- Submit the form.
Resources & Support
For details about the interview process and platform information, please check: https://talent.docs.mercor.com/welcome/welcomeFor any help or support, reach out to: support@mercor.com
PS: Our team reviews applications daily. Please complete your AI interview and application steps to be considered for this opportunity.
Key skills/competency
- AI Red-Teaming
- Prompt Injection
- Jailbreaking
- Adversarial ML
- Cybersecurity
- Vulnerability Assessment
- Risk Analysis
- Penetration Testing
- Socio-Technical Probing
- Documentation
How to Get Hired at Mercor
- Research Mercor's culture: Study their mission, values, recent news, and employee testimonials on LinkedIn and Glassdoor.
- Tailor your resume for AI Red-Teaming: Highlight relevant experience in adversarial AI, cybersecurity, or socio-technical probing.
- Prepare for the AI interview: Practice articulating your experience with red-teaming methodologies and communication skills.
- Showcase adversarial thinking: Emphasize your curiosity and ability to push systems to their breaking points in your application.
- Demonstrate adaptability: Be ready to discuss how you've handled diverse projects and customer needs in past roles.
Frequently Asked Questions
Find answers to common questions about this job opportunity
Explore similar opportunities that match your background