AI Safety Expert – English, Assamese
Employment Information
Report this job
Job expired or something wrong with this job?
Job Description
AI safety red teamer probing Mercor clients’ frontier AI models for jailbreaks, bias, and misuse. Producing human data, vulnerability classifications, and reproducible attack artifacts.
Responsibilities:
- Red-team conversational AI models and agents through jailbreaks, prompt injections, misuse cases, bias exploitation, and multi-turn manipulation
- Generate human data by annotating failures, classifying vulnerabilities, and flagging systemic risks
- Apply taxonomies, benchmarks, and playbooks to keep testing consistent
- Produce reproducible reports, datasets, and attack cases for customers
- Review AI outputs involving sensitive topics such as bias, misinformation, or harmful behaviors
- Uncover vulnerabilities automated tests miss
- Expand evaluation coverage and reduce production surprises
- Strengthen customer AI systems through adversarial testing
Requirements:
- Native fluency in English and Assamese
- Strong judgment about language and content; ability to assess whether AI responses are accurate, complete, and appropriate
- Ability to identify subtle errors, inconsistencies, and gaps
- Ability to follow guidelines and quality standards consistently
- Ability to explain reasoning clearly to technical and non-technical audiences
- Adaptability across projects, task types, and customers
- Nice-to-have: adversarial ML experience, including jailbreak datasets, prompt injection, RLHF/DPO attacks, or model extraction
- Nice-to-have: cybersecurity experience, including penetration testing, exploit development, or reverse engineering
- Nice-to-have: socio-technical risk experience, including harassment/disinformation probing, abuse analysis, or conversational AI testing
- Nice-to-have: psychology, acting, or writing experience for unconventional adversarial thinking
- Must be an independent contractor
- H1-B and STEM OPT candidates are not supported
Benefits:
- Fully remote role
- Flexible schedule; work can be completed on your own schedule
- Weekly payments via Stripe or Wise
- Opportunity to build experience in human data-driven AI red teaming
- Direct role in making AI systems more robust, safe, and trustworthy
- Collaborate with leading researchers
- Reasonable accommodations upon request
- Referral payments of up to $90 for successful referrals
Similar Jobs
AI Safety Red Teamer
AI Safety Red Teamer identifying vulnerabilities in frontier AI models for Mercor. Designing adversarial prompts and evaluating high-risk AI behavior with leading safety researchers.
AI Safety Expert, English, Dutch
AI safety experts red teaming conversational models for Mercor, which partners with AI labs to train frontier systems. Generating vulnerability data, attack cases, and reproducible safety reports.
AI Safety Expert – English, Tamil
AI safety red teamer probing conversational AI models for Mercor, which partners with leading AI labs to train frontier systems. Generating vulnerability data, attack cases, and reproducible reports.
AI Process Engineer
AI Process Engineer improving Arcanys’ recruitment, finance, sales and administrative processes. Building AI automations, coaching staff and measuring operational impact.
AI Safety Expert – English, Telugu
AI safety red teamer probing conversational AI models for Mercor. Generating adversarial datasets, vulnerability reports, and attack cases for frontier AI systems.
AI Safety Red Teamer
AI Safety Red Teamer stress-testing frontier AI models for Mercor, which partners with AI labs to train and enhance frontier systems. Identifying vulnerabilities across high-risk domains.
Community Manager – AI Community
Community Manager:in für snipKIs praktische KI-Lerncommunity. Moderation, Content und Engagement-Formate für die KI-Enablement-Community.
AI Safety Expert – English, Finnish
AI safety red teamer probing conversational AI models for Mercor’s human-data AI projects. Generating reproducible vulnerability data that strengthens frontier AI systems.
AI Safety Expert – English, Tamil
AI safety red teamer probing conversational AI models for Mercor, which partners with AI labs to train frontier systems. Generating vulnerability data, attack cases, and reproducible safety reports.
AI Safety Red Teamer
AI Safety Red Teamer testing frontier AI systems for Mercor’s AI training projects. Designing adversarial prompts and documenting vulnerabilities across high-risk domains.
AI Safety Red Teamer
AI Safety Red Teamer stress-testing frontier AI systems for Mercor and its AI-lab partners. Identifying vulnerabilities through adversarial prompts and safety evaluations.
AI Safety Expert – English, Telugu
AI red-teaming expert probing conversational models for Mercor, which partners with AI labs to train frontier systems. Finding vulnerabilities and producing reproducible safety data.
AI Safety Experts, English, Punjabi
AI red-team expert probing conversational models for Mercor, which partners with AI labs to train frontier systems. Generating vulnerability data, attack cases, and reproducible safety reports.
AI Safety Expert – English, Gujarati
AI safety red teamer probing conversational AI models for Mercor, which partners with leading AI labs and enterprises. Generating vulnerability data, attack cases, and reproducible safety evaluations.
AI Safety Expert, English, Gujarati
AI red team expert probing Mercor-partnered frontier AI models for vulnerabilities. Generating annotated datasets, attack cases, and reproducible safety reports in English and Gujarati.
AI Safety Experts – English, Punjabi
AI red-team contractor probing conversational models for Mercor, which partners with AI labs to train frontier systems. Testing jailbreaks, vulnerabilities, and harmful-content risks.
AI Safety Specialist
AI safety specialist supporting Mercor’s short-term AI safety project. Applying red-teaming and related domain expertise during a fast-paced remote sprint.
AI Safety Expert – English, Marathi
AI safety red teamer probing conversational AI models for Mercor, which partners with AI labs and enterprises to train frontier systems. Generating reproducible vulnerability data and attack cases.
AI Safety Expert – English, Tamil
AI safety red teamer probing conversational AI models for Mercor, which partners with leading labs to train frontier systems. Generating vulnerability data and reproducible attack artifacts.
AI Safety Expert, English, Punjabi
AI red-teaming experts probing conversational models for Mercor’s frontier AI safety projects. Generating vulnerability data, attack cases, and reproducible reports for AI labs and enterprises.