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 projects. 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
- 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 cyber, biosecurity, political content, misinformation, or scientific safety preferred
- Unable to support H1-B or STEM OPT candidates at this time
Benefits:
- Fully remote role
- Flexible schedule / work on your own schedule
- Weekly payments via Stripe or Wise
- Projects may be extended, shortened, or concluded early depending on needs and performance
- Competitive pay
- Opportunity to collaborate with leading AI researchers and safety teams
- Referral payments of up to $340 per successful referral, subject to restrictions
- Reasonable accommodations upon request
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 behaviors.
AI Safety Red Teamer
AI Safety Red Teamer stress-testing frontier AI models for Mercor. Identifying jailbreaks, hallucinations, and policy failures across high-risk domains.
AI Safety Red Teamer
AI Safety Red Teamer stress-testing frontier AI models for Mercor. Identifying jailbreaks, vulnerabilities, and safety failures through adversarial evaluation.
AI Safety Red Teamer
AI Safety Red Teamer stress-testing frontier AI models for Mercor, which partners with AI labs to train models. Finding vulnerabilities and improving model safety through adversarial evaluation.
AI Product Director – FinOps/ITFM
AI Product Director building brightfin’s FinOps AI platform for enterprise technology-spend optimization. Owning product strategy, pricing, design partners, and initial go-to-market execution.
AI Program Lead
AI Program Lead deploying agentic workflows across Salesforce and revenue systems. Improving sales productivity for Hyland’s enterprise content and automation platform.
GQA Technical Manager – AI
GQA AI Technical Manager leading BSI’s global AI certification and regulatory assessment programs. Managing conformity assessment, accreditation schemes, and AI compliance across Europe and the US.
AWS Certified AI Practitioner
AWS AI practitioner designing AI/ML solutions on AWS for government IT call centers. Automating workflows, analyzing interactions, and improving service delivery.
AI Response Labeler, Annotator – Italian Specialty
AI response evaluator comparing and rating AI-generated content in English and Italian for Blueprint Technologies. Applying Italian cultural expertise, factuality, reasoning, safety, and quality standards.
AI Response Labeler – Italian Specialty
AI response annotator comparing and evaluating AI-generated content in English and Italian for Blueprint, a technology solutions firm. Applying Italian cultural expertise, quality guidelines, and evidence-based judgment.
AI Response Labeler – Italian Specialty
AI response annotator comparing and evaluating AI-generated content in English and Italian. Applying Italian cultural expertise and structured quality standards for Blueprint’s technology solutions.
AI Response Labeler – Italian Specialty
AI response annotator comparing and evaluating English and Italian AI outputs for Blueprint Technologies. Applying Italian cultural expertise, annotation guidelines, and quality standards across varied tasks.
AI Response Labeler – Italian Specialty
AI response annotator comparing and evaluating AI-generated content in English and Italian. Applying Italian cultural expertise and structured quality guidelines for Blueprint’s technology solutions.
AI Response Labeler, Annotator – Italian Specialty
AI response annotator comparing and evaluating AI-generated content in English and Italian. Applying Italian cultural expertise and structured quality standards for Blueprint’s technology solutions.
AI Response Labeler – Italian Specialty
AI response evaluator comparing English and Italian outputs for Blueprint, a technology solutions firm. Assessing accuracy, reasoning, cultural context, safety, and usefulness across varied AI tasks.
AI Response Labeler – French Specialty
AI response annotator comparing AI-generated content in English and French for Blueprint Technologies. Assessing accuracy, reasoning, cultural fit, safety, and overall usefulness.
AI Response Labeler – French Specialty
AI response labeler comparing and evaluating English/French AI outputs for Blueprint, a technology solutions firm. Applying French cultural expertise and structured quality guidelines.
AI Response Labeler – French Specialty
AI Response Labeler evaluating French and English AI outputs for accuracy, relevance, safety, and cultural fit. Supporting Blueprint’s AI, cloud, data, and technology solutions work.
AI Response Labeler – French Specialty
AI Response Labeler evaluating AI-generated content in English and French for Blueprint, a technology solutions firm serving AI, cloud, data, and product development needs. Applying French cultural expertise and structured quality criteria.
AI Product Builder, Vibe Coding Bootcamp
AI Product Builder bootcamp training digital professionals to build and deploy AI products. Developing prompt engineering, automation, and multi-agent system skills without prior programming experience.