Evaluate the safety, quality, and alignment of frontier AI models by reviewing policy-sensitive content, applying AI safety standards, identifying model failures, and helping improve next-generation AI systems.
AI Safety Red Teamer
Remote (Global)
$70 – $84/hr
July 16, 2026
Job description
Role Overview
Mercor is seeking experienced AI Safety Red Teamers to identify vulnerabilities in frontier AI systems through adversarial testing. In this role, you will design challenging prompts, uncover model weaknesses, evaluate AI behavior across high-risk scenarios, and provide structured feedback that improves AI robustness, alignment, and safety.
This is a flexible remote contract opportunity for professionals with expertise in AI Safety, Red Teaming, Trust & Safety, cybersecurity, or other high-risk evaluation domains who want to help secure next-generation AI systems.
Key Responsibilities
Perform AI Red Teaming
- Design adversarial prompts to stress-test frontier AI models.
- Evaluate AI responses under challenging and ambiguous scenarios.
- Identify vulnerabilities in model behavior.
Evaluate High-Risk Domains
- Test AI performance across:
- Misinformation
- Cybersecurity
- Biosecurity
- Fraud
- Political content
- Other policy-sensitive and grey-area topics
Identify Model Failures
Detect:
- Jailbreaks
- Unsafe behaviors
- Hallucinations
- Policy violations
- Alignment failures
Document vulnerabilities and contribute to AI safety benchmarking.
Collaborate with AI Safety Teams
- Work alongside AI researchers and safety specialists.
- Help improve model robustness, alignment, and overall safety through structured evaluations.
Required Qualifications
Bachelor's degree or higher in one of the following (or a related discipline):
- Computer Science
- Cybersecurity
- Journalism
- Communications
- Psychology
- Biology
- Chemistry
- Public Policy
5+ years of professional experience in:
- AI Safety
- AI Red Teaming
- Trust & Safety
- Cybersecurity
- Investigative Journalism
- Life Sciences
- Related technical or policy fields
Strong analytical reasoning and written communication skills.
Experience designing adversarial prompts or evaluating frontier AI systems.
Preferred Qualifications
Experience with:
- AI Red Teaming
- RLHF
- SFT
- AI Alignment
- Trust & Safety
Familiarity with:
- Jailbreak testing
- Prompt engineering
- Adversarial evaluation methodologies
Expertise in one or more of:
- Cybersecurity
- Biosecurity
- Political content
- Misinformation
- Scientific safety
Compensation
- $70–$84 USD per hour
Work Arrangement
- Remote
- Independent contractor
- Flexible schedule
- Weekly payments via Stripe or Wise
Apply now
You will be redirected to the company's website to complete your application.
Role Title: LLM Red-Teamer Role Type: Contractor Location: Remote micro1 is engaging LLM Red-Teamers to contribute to a high-impact customer project focused on the evaluation and improvement of frontier language models.
Mercor is seeking bilingual AI Safety Experts fluent in both English and Marathi to help evaluate and strengthen the safety of frontier AI systems. This role focuses on red teaming AI models by identifying vulnerabilities, testing misuse scenarios, and generating high-quality…
Mercor is seeking bilingual AI Safety Experts fluent in both English and Odia to help evaluate and strengthen the safety of frontier AI systems. This role focuses on red teaming AI models by identifying vulnerabilities, testing misuse scenarios, and generating high-quality…