AI Safety Red Teamer
Employment Information
Report this job
Job expired or something wrong with this job?
Job Description
AI Safety Red Teamer stress-testing frontier AI models for Mercor’s AI training partnerships. Identifying vulnerabilities and improving model alignment, robustness, and safety.
Responsibilities:
- Design adversarial prompts to stress-test frontier AI models
- Identify jailbreaks, unsafe behaviours, hallucinations, and policy failures
- Evaluate model robustness across misinformation, cyber, biosecurity, fraud, political content, and other sensitive domains
- Document vulnerabilities and contribute to safety benchmarking and red-teaming reports
- Collaborate with AI researchers to improve model alignment, robustness, and safety
- Work on projects focused on training and enhancing AI systems
Requirements:
- Bachelor's degree or higher in Computer Science, Cybersecurity, Journalism, Communications, Psychology, Biology, Chemistry, Public Policy, or a related discipline
- 5+ years of professional experience in AI Safety, AI Red Teaming, Trust & Safety, cybersecurity, investigative journalism, life sciences, or a related field
- Strong analytical reasoning, prompt design, and written communication skills
- Experience designing adversarial prompts or evaluating frontier AI systems
- Preferred: experience with AI Red Teaming, RLHF, SFT, AI Alignment, or Trust & Safety
- Preferred: familiarity with jailbreak testing, prompt engineering, or adversarial evaluation methodologies
- Preferred: expertise in grey-area domains including cyber, biosecurity, political content, misinformation, or scientific safety
- Must not require H1-B or STEM OPT sponsorship/support
Benefits:
- Fully remote role
- Flexible schedule; work can be completed on your own schedule
- Weekly payments via Stripe or Wise based on services rendered
- Projects may be extended, shortened, or concluded early depending on needs and performance
- Competitive payment
- Opportunity to work alongside leading AI researchers and safety teams
- Opportunity to influence frontier AI safety and alignment
- Referral payments of up to $340 per successful referral
Similar Jobs
AI Safety Red Teamer
AI Safety Red Teamer identifying vulnerabilities in frontier AI models for Mercor’s AI lab partnerships. Designing adversarial prompts and evaluating high-risk model behavior.
AI Safety Expert – English, Portuguese
AI safety red teamer probing conversational models for jailbreaks, prompt injections, and systemic risks. Producing human-data artifacts that help Mercor customers build safer frontier AI.
AI Safety Experts – English, Bengali
AI safety red team expert probing Mercor’s partner AI models for vulnerabilities. Generating reproducible adversarial data, reports, and attack cases to improve model safety.
Principal AI Search – Conversation Architect
Principal AI architect building conversational search and commerce orchestration for OleOle’s global football super app. Designing LLM, agent, retrieval, and recommendation systems across real-time sports services.
AI Workflow Engineer
AI workflow engineer building Python and GenAI automation for BlueCross BlueShield of Tennessee. Supporting Treasury and Internal Audit workflow modernization, governance, training, and adoption.
AI Prompt Engineer
Prompt Systems Engineer designing and evaluating AI agents for Noodle, a higher-education strategy, services, and technology partner. Improving enrollment, learning, and student-support experiences.
Senior AI, Product Enablement Specialist
Senior AI and Product Enablement Specialist creating technical labs and training. Enabling customers on Sysdig’s cloud-native security solutions across containers, Kubernetes, Linux, and public cloud.
Senior AI & Product Enablement Specialist
Senior AI and Product Enablement Specialist building technical labs and training for Sysdig’s cloud security platform. Automating Kubernetes, Linux, and public-cloud learning environments.
AI Automation Lead
AI automation lead building workflows, CRM systems, and internal tools for Nucleus Network’s advisory, venture, and events businesses. Improving relationship data, efficiency, and scalable operations.
Engineer I, AI Agents
Engineer I building AI agent platforms for AARP, the nonprofit empowering older Americans. Developing LLM integrations, workflows, and enterprise solutions.
AI Leadership Industry Expert – University, Academic Experience
AI Leadership Facilitator delivering postgraduate AI Leadership education for peopleworth. Leading live sessions, mentoring learners, and supervising academic facilitators remotely.
AI Builder Grant
AI Builder Grant providing Claude access to university students in Austria, Germany, and Switzerland. Supporting personal AI projects and exposure to real-world artificial intelligence tooling.
AI Safety Red Teamer
AI Safety Red Teamer stress-testing Mercor’s partner frontier AI models. Identifying jailbreaks, hallucinations, and policy failures across high-risk domains.
Trainer for CAD and Artificial Intelligence in Engineering
CAD- und KI-Trainer:in für digitale Produktentwicklung im Maschinenbau. Vermittlung generativer Design- und Engineering-Workflows an Fachkräfte.
CAD and Artificial Intelligence Trainer – Engineering
CAD- und KI-Trainer:in für die Weiterbildung von Maschinenbau-Fachkräften. Vermittlung generativer Design- und KI-gestützter Engineering-Workflows für die digitale Produktentwicklung.
Data Management & AI Analyst, Healthcare
Data-Analyst-Weiterbildung für Klinik-, Pflege- und Verwaltungsdaten bei DataSmart Point. Lernen von SQL, Power BI, Python und Predictive Analytics für digitale Gesundheitsprojekte.
AI Safety Expert – English, Assamese
AI safety red-teamer probing conversational models for Mercor’s frontier AI projects. Generating adversarial datasets, vulnerability reports, and attack cases to strengthen AI systems.
Marketing Expert – Marketing Analytics, AI Agent Environments
Marketing analytics expert designing realistic task environments for Mercor’s AI-agent training projects. Evaluating data diagnosis, attribution, reporting, and multi-tool decision-making.
AI Safety Expert – English, Danish
AI safety red teamer probing frontier AI models for Mercor. Testing jailbreaks, vulnerabilities, and harmful behaviors to generate safer human-data-driven AI systems.
Management Consultant – AI Strategy Evaluation
Management Consultant evaluating AI-generated strategy responses for Gramian Consultancy. Creating consulting prompts, reference answers, and feedback to improve model reasoning.