AI Safety Experts — English & Assamese | $20-$22/hr Remote
Overview
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.
What You'll Do4
- 1Conduct adversarial testing on conversational AI models, including jailbreaks, prompt injections, misuse scenarios, and bias exploitation across multi-turn interactions.
- 2Produce detailed annotations of model failures, classify vulnerability types, and flag systemic risks to help improve safety guardrails.
- 3Follow established taxonomies, benchmarks, and testing playbooks to ensure consistent and comparable evaluations.
- 4Create comprehensive reports and datasets that document reproducible attack cases, enabling customers to directly strengthen their AI systems.
Requirements3
- 1Native or bilingual fluency in English and Assamese (both written and spoken) is mandatory for this role.
- 2Prior experience in AI red teaming, adversarial machine learning, or cybersecurity—with a proven ability to surface vulnerabilities automated tests miss.
- 3Structured approach to probing: ability to use frameworks and benchmarks rather than random hacking, plus clear communication of risks to both technical and non-technical audiences.
Who Should Apply
We're looking for a curious, adversarial-minded individual who instinctively looks for weak points in systems and enjoys methodically breaking them. You should be comfortable working with sensitive content (e.g., bias, misinformation) and thrive on clear documentation. Ideal candidates bring experience from red teaming, penetration testing, or socio-technical risk analysis—and are eager to play a direct role in making AI safer.
Salary Insight
Hourly compensation ranges from $20.00 to $22.00, based on experience and project scope.
Application Tip
When applying, include a specific example of a time you uncovered a vulnerability that automated testing missed—describe the attack method, the system you tested, and the impact of your findings.
Similar open positions
Explore active roles that match your skills and interests.
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.
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.
Mercor
VerifiedAI Safety Experts — English & Punjabi | $20-$22/hr Remote
We're looking for bilingual experts fluent in English and Punjabi to help stress-test and improve the safety of AI conversational models. In this remote, project-based role, you'll probe AI systems for hidden vulnerabilities—from jailbreaks to bias exploitation—and deliver actionable data that makes these models more trustworthy. This is hands-on adversarial testing with a direct impact on real-world AI safety.
Mercor
VerifiedAI Safety Red Teamer | $70-$84/hr Remote
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.
Mercor
VerifiedGeneralist - English & Assamese | $15-$20/hr Remote
In this contract role, you'll help refine AI by evaluating its Assamese-language responses. You'll identify strengths and weaknesses, fact-check using public sources, and provide clear English feedback to guide the development of a near-perfect AI assistant. This is a part-time, remote opportunity paying $15–$20 per hour.
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.