Adversarial AI 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
About the Adversarial AI Specialist Role 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.
Position Details
This is an Adversarial AI Specialist position. It is offered as a full-time or part-time contract work, with compensation at $50/hour. This is a remote role, with geography restricted to the USA and Japan. A commitment of 20+ hours per week is required.
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 maintain consistent testing.
- Document reproducibly to produce 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 Language Skills Required: Native-level fluency in English & Japanese.
- Prior experience in red teaming (AI adversarial work, cybersecurity, socio-technical probing).
- Ability to explain risks clearly to technical and non-technical stakeholders.
- Adaptability to move 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.
- Skills in Creative probing: psychology, acting, writing for unconventional adversarial thinking.
Compensation & Legal
This is an hourly contractor position, paid weekly via Stripe Connect.
Application Process (Takes 20–30 mins to complete)
Please follow these steps to apply:
- 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
- Prompt Injection
- Jailbreaking
- Adversarial ML
- Cybersecurity
- Vulnerability Analysis
- Risk Assessment
- Conversational AI
- Native English Fluency
- Native Japanese Fluency
How to Get Hired at Mercor
- Research Mercor's mission: Study their focus on connecting top talent with leading AI research labs and their investor backing.
- Tailor your resume for AI security: Highlight specific experience in adversarial AI, cybersecurity, red teaming, and socio-technical probing.
- Prepare for the AI interview: Understand that Mercor uses an AI-based interview process; practice articulating your experience concisely and clearly.
- Showcase language proficiency: Emphasize your native-level fluency in both English and Japanese as it's a critical 'must-have' qualification.
- Demonstrate independent work ethic: Provide examples of successfully managing projects asynchronously and delivering high-quality results autonomously.
Frequently Asked Questions
Find answers to common questions about this job opportunity
Explore similar opportunities that match your background