AI Safety Expert – English, Bengali
Employment Information
Report this job
Job expired or something wrong with this job?
Job Description
AI safety red teamer probing frontier AI models for Mercor, which partners with leading labs and enterprises to train models. Generating vulnerability data 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 that automated tests miss
- Expand evaluation coverage and reduce production surprises
- Strengthen customer AI systems through reproducible artifacts
- Collaborate with leading researchers on projects training and enhancing frontier AI systems
Requirements:
- Fluent/native fluency in English and Bengali is required
- Strong judgment about language and content
- Ability to assess whether AI responses are accurate, complete, and appropriate, and explain why
- Ability to notice 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
- Independent contractor status
- Must not be an H1-B or STEM OPT candidate
- 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
Benefits:
- Fully remote role
- Flexible schedule / work on your own schedule
- Weekly payments via Stripe or Wise
- Wellness resources and clear guidelines for higher-sensitivity projects
- Opportunity to build experience in human data-driven AI red teaming
- Opportunity to help make AI systems more robust, safe, and trustworthy
- Competitive pay
- Collaboration with leading researchers
- Referral payments of up to $90 per successful referral
Similar Jobs
AI Safety Expert – English, Assamese
AI safety experts red-teaming conversational AI models for Mercor, which partners with leading AI labs to train frontier systems. Generating vulnerability data, attack cases, and reproducible safety reports.
AI Safety Expert – English, Gujarati
AI red-teaming expert probing conversational models for Mercor, which partners with AI labs to train frontier systems. Generating adversarial data, vulnerability reports, and reproducible attack cases.
AI Safety Expert, English, Gujarati
AI red-teaming expert probing Mercor customer models for jailbreaks, bias, and misuse. Generating reproducible human-data artifacts that improve frontier AI safety.
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 Safety Experts, English – Marathi
AI red-teaming experts testing Mercor’s frontier models through adversarial English and Marathi analysis. Probing vulnerabilities and producing datasets that make customer AI systems safer.
AI Safety Expert – English, Bengali
AI safety red teamer probing conversational AI models for Mercor, which partners with AI labs to train frontier systems. Generating vulnerability data and reproducible attack cases.
AI Safety Expert – English, Urdu
AI safety red teamer probing Mercor-partnered frontier AI models for vulnerabilities. Testing conversational systems and generating actionable human data in English and Urdu.
AI Safety Expert, English – Odia
AI safety expert red-teaming conversational AI models for Mercor, which partners with leading AI labs and enterprises. Generating adversarial data, vulnerability annotations, and reproducible safety artifacts.
AI Safety Experts – English, Assamese
AI red-teaming contractor probing conversational models for Mercor, which partners with AI labs and enterprises to train frontier systems. Generating vulnerability data and reproducible attack cases.
AI Safety Expert – English, Gujarati
AI safety red teamer probing conversational AI models for Mercor, which partners with AI labs to train frontier systems. Creating vulnerability data, attack cases, and reproducible reports.
AI Safety Experts, English, Kannada
AI safety experts red-teaming conversational AI models for Mercor, which partners with leading AI labs. Generating human data and reproducible vulnerability reports.
AI Safety Expert, English – Bengali
AI red-team expert probing conversational models for jailbreaks, bias, and misuse. Generating reproducible safety data for Mercor’s frontier AI lab and enterprise customers.
AI Safety Expert – English, Telugu
AI safety experts red-teaming conversational AI for Mercor’s frontier model training projects. Testing vulnerabilities, annotating failures, and producing reproducible safety data.
LLM AI Quality Analyst, Chinese
Chinese-speaking AI Quality Analyst evaluating personalized responses for a leading AI technology company. Creating prompts, reviewing accuracy, detecting hallucinations, and providing detailed rationales.
Lead Marketer – AI Usage Automation
Lead AI-powered customer automation marketing at HubSpot, an AI-powered customer platform. Design personalized journeys, experiments, and communications that help businesses grow.
Lead Marketer, AI Usage Automation
Lead marketer defining AI-powered customer automation and personalized digital journeys at HubSpot, an AI-powered customer platform. Driving experimentation, optimization, and executive reporting.
Lead Marketer, AI Usage Automation
Lead marketer defining AI-powered customer automation and personalized digital journeys. HubSpot provides an AI-powered customer platform connecting marketing, sales, and service.
AI Safety Expert, English, Portuguese
AI safety red teamer probing Mercor’s frontier AI models for vulnerabilities. Generating reproducible attack data to make customer systems safer and more robust.
AI Safety Red Teamer
AI Safety Red Teamer stress-testing frontier AI models for Mercor, which partners with AI labs to train frontier systems. Identifying vulnerabilities and improving model safety through adversarial testing.
AI Specialist
Especialista em IA liderando projetos de automação, agentes virtuais e governança. Conectando soluções de inteligência artificial às necessidades do Grupo Odilon Santos.