Lead Adversarial 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.
Mercor is seeking a Lead Adversarial AI Red-Teamer to join our team. This is a contract position with options for full-time or part-time work, offering competitive compensation and the flexibility of remote work.
Role Responsibilities
- Red team conversational AI models and agents to identify jailbreaks, prompt injections, misuse cases, and bias exploitation.
- 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 that customers can act on.
- Work independently and asynchronously to meet deadlines while improving AI model performance.
Qualifications
Must-Have
- Fluent in English and Italian with native-level fluency.
- Prior red teaming experience in AI adversarial work, cybersecurity, or socio-technical probing.
- Ability to explain risks clearly to technical and non-technical stakeholders.
Preferred
- Experience in Adversarial ML, Cybersecurity, or socio-technical risk analysis.
- Skills in jailbreak datasets, prompt injection, RLHF/DPO attacks, or model extraction.
Compensation & Legal
This is an hourly contractor position, paid weekly via Stripe Connect. Compensation is set at $50/hour, with a commitment of 20+ hours/week.
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.
Our team reviews applications daily. Please complete your AI interview and application steps to be considered for this opportunity.
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
Key skills/competency
- AI Red Teaming
- Adversarial AI
- Prompt Injection
- Jailbreaking
- Bias Exploitation
- Vulnerability Classification
- Cybersecurity
- Socio-technical Probing
- Data Annotation
- Risk Analysis
How to Get Hired at Mercor
- Research Mercor's culture: Study their mission, values, recent news, and employee testimonials on LinkedIn and Glassdoor to understand their focus on elite AI talent and research.
- Tailor your resume for AI Red Teaming: Highlight specific experience in adversarial AI, cybersecurity, prompt injection, and bias exploitation. Emphasize projects demonstrating your ability to identify and document AI vulnerabilities.
- Prepare for the AI interview: Practice articulating your red teaming experience and technical skills clearly. Be ready to discuss how you've identified jailbreaks or misuse cases in past roles.
- Showcase your bilingual proficiency: Since native English and Italian fluency is required, be prepared to demonstrate this during the interview process, potentially through case studies or discussions in both languages.
- Demonstrate structured problem-solving: Emphasize your ability to follow taxonomies and playbooks, documenting findings reproducibly with detailed reports and attack cases for the Lead Adversarial AI Red-Teamer role.
Frequently Asked Questions
Find answers to common questions about this job opportunity
Explore similar opportunities that match your background