AI Safety Red Teamer | $70-$84/hr Remote
Overview
Join a team focused on strengthening the safety of advanced AI systems by uncovering their hidden weaknesses. As an AI Safety Red Teamer, you'll design clever prompts to stress-test models, spot dangerous behaviors, and help improve how these systems handle tricky real-world scenarios. This remote contractor role lets you work alongside top researchers while earning $70–$84 per hour.
What You'll Do5
- 1Create adversarial prompts that push frontier AI models to their limits, revealing potential failure points.
- 2Identify and document jailbreaks, unsafe outputs, hallucinations, and policy breaches in model behavior.
- 3Test model performance across high-risk areas including misinformation, cybersecurity, biosecurity, and political content.
- 4Collaborate with AI researchers to refine model alignment and boost overall robustness.
- 5Compile clear vulnerability reports and contribute to safety benchmarks and red-teaming documentation.
Requirements4
- 1A bachelor’s degree or higher in fields like Computer Science, Cybersecurity, Journalism, or a related discipline.
- 2At least 5 years of professional experience in AI safety, red teaming, trust & safety, or investigative work.
- 3Strong skills in analytical reasoning, prompt engineering, and written communication to document findings clearly.
- 4Hands-on experience designing adversarial tests or evaluating frontier AI systems for vulnerabilities.
Who Should Apply
This role is ideal for someone who enjoys thinking like an attacker to make AI systems safer. You're curious, methodical, and have a knack for crafting prompts that reveal hidden flaws. If you have a background in safety research, cybersecurity, or investigative work and want to shape how cutting-edge models handle grey-area challenges, this is your opportunity.
Salary Insight
The position pays an hourly rate of $70–$84, reflecting the specialized skill set required for adversarial testing of advanced AI.
Application Tip
When applying, include a short portfolio or example of a prompt you designed that uncovered a realistic edge case in a language model — this shows your hands-on red-teaming approach.
Similar open positions
Explore active roles that match your skills and interests.
Mercor
VerifiedAI Safety Practitioner | $60-$70/hr Remote
We’re seeking a sharp evaluator to test frontier AI models for safety, quality, and alignment. You’ll assess responses on complex, policy-sensitive topics like misinformation and biosecurity, applying structured rubrics to catch unsafe or misaligned outputs. Your feedback will directly shape how these models behave for millions of users worldwide.
Mercor
VerifiedCybersecurity SWE — AI Safety | $60-$90/hr Remote
This part-time remote role invites a cybersecurity engineer to apply their skills in AI safety — no prior machine learning background needed. You'll work hands-on evaluating how advanced AI models handle sensitive security topics, with full training on the workflow. It's a unique chance to blend deep security knowledge with the frontier of AI development.
Mercor
VerifiedAI Safety Experts — English & Assamese | $20-$22/hr Remote
We're assembling a remote team of AI red teamers to stress-test conversational models and uncover hidden vulnerabilities. In this role, you'll probe AI systems with adversarial inputs—jailbreaks, prompt injections, bias exploitation—and generate the high-quality human data that makes AI safer for real-world use. Fluency in both English and Assamese is essential, as you'll review sensitive outputs and document reproducible attack cases. This project is ideal for structured, curious thinkers who enjoy pushing systems to their limits.
Mercor
VerifiedAI Safety Experts — English & Odia | $20-$22/hr Remote
Mercor is looking for native English and Odia speakers to join a remote red team that stress-tests AI conversational models. You'll probe for vulnerabilities using adversarial techniques like jailbreaks and prompt injections, generating critical data that makes AI systems safer. This text-based project covers sensitive topics with clear guidelines and wellness support, allowing you to work on high-impact safety work from anywhere.
Micro1
VerifiedRed Team Lead (Offensive Cybersecurity) | $50-$90/hr Remote
This remote contractor role with micro1 puts your offensive cybersecurity expertise to work in a unique way: you'll help train next-generation AI systems by designing evaluation frameworks and attack simulations. No prior AI experience is required—your hands-on knowledge of exploit chains, cloud/appsec, and social engineering is what makes you the ideal candidate. You'll shape how models learn about real-world threats while operating under strict ethical boundaries.
Mercor
VerifiedAI Safety Experts — English & Bengali | $20-$22/hr Remote
Neon is seeking bilingual (English & Bengali) AI safety experts to join a remote red teaming project. In this role, you'll proactively probe conversational AI models using adversarial techniques like jailbreaks and prompt injections to uncover vulnerabilities before they reach production. Your work directly contributes to making AI systems more robust and trustworthy.