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.
Position: AI Red-Teamer
Mercor is seeking an AI Red-Teamer to join their team. This role can be full-time or part-time, offers competitive hourly compensation, and is remote-friendly for candidates within US time zones, restricted to the US, UK, and 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.
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/disinformation probing and abuse analysis.
- Creative probing skills in psychology, acting, or writing for unconventional adversarial thinking.
Compensation & Legal
- Hourly contractor position.
- Compensation varies by project, customer, and content category.
Application Process (Takes 20–30 mins to complete)
To apply for the AI Red-Teamer role, please follow these steps:
- 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: talent.docs.mercor.com/welcome/welcome
For 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
- Adversarial Machine Learning
- Vulnerability Classification
- Cybersecurity Probing
- Risk Management
- Exploit Development
- Socio-Technical Risk
- Structured Testing
- Communication Skills
How to Get Hired at Mercor
- Research Mercor's mission: Study their focus on connecting talent with AI research and their investor backing to understand their vision.
- Tailor your AI Red-Teamer resume: Highlight specific red-teaming, adversarial AI, or cybersecurity project experience.
- Prepare for the AI interview: Practice articulating your experience with prompt injection, jailbreaks, and vulnerability classification clearly.
- Showcase adversarial mindset: Demonstrate curiosity and a structured approach to breaking systems during the interview process.
- Emphasize communication skills: Be ready to explain complex technical risks to both technical and non-technical stakeholders effectively.
Frequently Asked Questions
Find answers to common questions about this job opportunity
Explore similar opportunities that match your background