AI Red Team Specialist
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
AI Red Team Specialist at 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.
About The Job
As an AI Red Team Specialist, you will be crucial in ensuring the safety and robustness of conversational AI models and agents by identifying and mitigating potential risks. This role involves meticulous testing, detailed documentation, and a structured approach to adversarial work.
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 that customers can act on.
- Work independently and asynchronously to meet deadlines while improving AI model performance.
Qualifications
Must-Have
- Native-level fluency in English and Spanish.
- Prior red teaming experience in AI adversarial work, cybersecurity, or socio-technical probing.
- Structured approach using frameworks or benchmarks.
- Strong communication skills to explain risks clearly to technical and non-technical stakeholders.
- Adaptability to thrive on moving across projects and customers.
Preferred
- 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.
Compensation & Legal
Hourly contractor, Paid weekly.
Application Process (Takes 20–30 mins to complete)
- Upload resume
- AI interview based on your resume
- Submit form
Resources & Support
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
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
- Adversarial Machine Learning
- Cybersecurity
- Prompt Injection
- Jailbreaking
- Vulnerability Assessment
- Data Annotation
- Risk Classification
- Socio-technical Probing
- Strong Communication
How to Get Hired at Mercor
- Research Mercor's mission: Study their focus on connecting elite talent with AI research, their innovative approach, and their notable investors like Benchmark and Peter Thiel.
- Tailor your resume: Highlight specific experience in AI red teaming, adversarial ML, cybersecurity, and socio-technical probing, emphasizing tangible results and structured methodologies.
- Prepare for the AI interview: Practice articulating complex security concepts clearly, demonstrating your problem-solving skills, and showcasing your adaptability to diverse projects.
- Showcase language fluency: Emphasize your native-level fluency in both English and Spanish, as this is a must-have qualification for effective communication and risk explanation.
- Demonstrate structured thinking: Provide examples of how you've used frameworks, benchmarks, or playbooks in previous roles to ensure consistent and reproducible testing outcomes.
Frequently Asked Questions
Find answers to common questions about this job opportunity
Explore similar opportunities that match your background