AI Safety Red Teamer
Employment Information
Report this job
Job expired or something wrong with this job?
Job Description
AI Safety Red Teamer identifying vulnerabilities in frontier AI systems for Mercor. Designing adversarial prompts and evaluating high-risk model behavior with AI researchers.
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
- Complete projects on an individual schedule; projects may be extended, shortened, or concluded early based on needs and performance
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 cyber, biosecurity, political content, misinformation, or scientific safety
- Independent contractor engagement
- Must be able to work in one of the listed eligible locations
- H1-B and STEM OPT candidates are not supported
Benefits:
- Fully remote work
- Flexible schedule; work can be completed on your own schedule
- Weekly payments via Stripe or Wise based on services rendered
- Potential project extensions
- Competitive pay
- Collaboration with leading AI researchers and safety teams
- Opportunity to influence frontier AI safety and model development
- Reasonable accommodations upon request
- Referral bonus of up to $340 per successful referral
Similar Jobs
Senior Marketing Strategy, AI Evaluation Specialist
Senior marketing strategist designing evaluation tasks and rubrics for generative AI models. Assessing AI-generated marketing content using brand, growth, and performance expertise.
AI Evaluation Guidelines & Rubric Specialist
AI evaluation specialist developing precise rater guidelines and scoring rubrics for generative AI programmes. Translating complex requirements across finance, legal, retail, insurance, and sports domains.
U.S. Licensed Dermatologist – AI Dermatology Research
U.S.-licensed dermatologist reviewing skin images and AI-generated assessments for 24-MAG LLC’s dermatology research. Establishing clinical guidelines and improving medically grounded AI systems.
AI Safety Red Teamer
AI Safety Red Teamer adversarially testing frontier AI models for Mercor, which partners with AI labs to train and enhance them. Documenting vulnerabilities across high-risk domains.
AI Safety Red Teamer
AI Safety Red Teamer stress-testing frontier AI models for Mercor. Designing adversarial prompts and documenting vulnerabilities to improve AI alignment and safety.
AI Data & Insights Officer
AI Data & Insights Officer turning event and luxury-travel business data into reliable intelligence. Building RAG, dashboards and agent-performance insight for Worldwide Events Group.
AI Data & Insights Officer
AI Data & Insights Officer transforming Worldwide Events Group’s MICE and luxury travel data into reliable intelligence. Building RAG knowledge systems, dashboards and measurable agent performance insights.
Data & AI Analyst
Data & AI Analyst transforming insurance marketing data into actionable insights, dashboards, and AI-powered automation. Building scalable solutions with SQL, BigQuery, Tableau, Python, and emerging AI tools.
AI Safety Red Teamer
AI Safety Red Teamer stress-testing frontier AI models for Mercor. Designing adversarial prompts and documenting vulnerabilities across high-risk domains.
AI Safety Expert, English, Finnish
AI red team expert testing Mercor’s frontier AI models through jailbreaks, prompt injections, and adversarial data generation. Producing reproducible vulnerability reports that improve AI safety.
AI Director
AI Director leading production AI architecture, governance, and client strategy at Futurice, a data-and-AI consultancy. Growing UK capability through consulting, business development, mentoring, and hiring.
Independent Zen Ambassador – AI Solutions
Ambassadeur freelance prospectant des dirigeants et les connectant à des solutions IA et experts B2B. David assure la vente, avec rémunération au succès et bonus.
Junior AI, Product Enablement Specialist
Junior enablement specialist building AI-assisted cloud-security training labs and technical content for Sysdig. Supporting DevOps training delivery, workshops, automation, and courseware development.
Head of AI – Processes
Head of AI & Processes leading AI consulting, process transformation, and automation growth. Developing LM IT Services’ practice, team, portfolio, and international customer projects.
Delivery Director – AI Foundry, Anthropic Business
Delivery Director leading NewRocket’s enterprise AI and Anthropic services portfolio. Driving delivery excellence, client growth, responsible AI adoption, and operational performance.
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’s AI training projects. Identifying vulnerabilities and improving model alignment, robustness, and safety.
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.