AI Safety Red Teamer
Employment Information
Report this job
Job expired or something wrong with this job?
Job Description
AI Safety Red Teamer designing adversarial prompts and uncovering vulnerabilities in Mercor’s frontier AI projects. Evaluating model behavior across high-risk domains and supporting AI safety research.
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 one or more grey-area domains, including cyber, biosecurity, political content, misinformation, or scientific safety
- Must be able to work as an independent contractor
- Mercor is unable to support H1-B or STEM OPT candidates at this time
Benefits:
- Fully remote role that can be completed on your own schedule
- Weekly payments via Stripe or Wise based on services rendered
- Projects can be extended, shortened, or concluded early depending on needs and performance
- Opportunity to work on cutting-edge adversarial testing alongside leading AI researchers and safety teams
- Opportunity to influence how AI systems respond to complex, real-world safety challenges
- Referral payments of up to $340 for each successful referral, subject to referral limits
- Reasonable accommodations available upon request
Similar Jobs
AI Safety Expert – English, Kannada
AI Safety Experts red-teaming conversational models for Mercor, which partners with AI labs to train frontier systems. Probing vulnerabilities and producing reproducible safety data.
AI Safety Expert – English, Kannada
AI safety red teamer probing conversational AI models for Mercor, which partners with leading AI labs to train frontier systems. Creating vulnerability data, attack cases, and reproducible reports.
AI Safety Expert – English, Marathi
AI safety red-teamer probing Mercor’s frontier AI models with adversarial English and Marathi inputs. Generating vulnerability annotations, attack cases, datasets, and reproducible reports.
Staff AI Builder
Staff AI Builder designing and shipping production GenAI systems for Robots and Pencils’ enterprise clients. Leading agentic AI, RAG, AWS architecture, reliability, and technical mentoring.
AI Benchmark Engineer, Native Language Specialist – Chinese
AI benchmark engineer building Chinese-language Terminal-Bench tasks for Lilt’s multilingual AI platform. Validating coding agents, reference implementations, and deterministic verifiers.
AI Benchmark Engineer, Native Language Specialist – Chinese
AI benchmark engineer creating Chinese-language Terminal-Bench tasks for Lilt’s multilingual AI platform. Validating coding agents, verifier scripts, and multilingual software robustness.
AI Benchmark Engineer, Native Language Specialist – Arabic
Arabic AI benchmark engineer designing Terminal-Bench tasks for Lilt’s multilingual AI and human-verified language services. Building multilingual assets, verifiers, and calibration workflows for coding agents.
AI Benchmark Engineer, Native Language Specialist – Arabic
Arabic-speaking benchmark engineer designing Terminal-Bench tasks for LILT’s multilingual AI evaluation suite. Building datasets, verifiers, and calibrated tests for coding agents.
AI Safety Experts – English, Telugu
AI safety red-teamer probing conversational models for Mercor’s human-data AI training projects. Generating vulnerability datasets, attack cases, and reproducible reports to strengthen frontier AI systems.
AI Safety Expert – English, Tamil
AI red-team 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, Kannada
AI safety red teamer probing Mercor’s frontier AI models for jailbreaks, bias, and vulnerabilities. Generating reproducible human-data artifacts for AI labs and enterprise customers.
AI Safety Red Teamer
AI Safety Red Teamer identifying vulnerabilities in frontier AI systems for Mercor. Designing adversarial prompts and evaluating high-risk model behavior.
AI Safety Expert – English, Tamil
AI red team expert probing conversational models for Mercor, which partners with AI labs to train frontier systems. Testing vulnerabilities and producing actionable safety data.
Associate Director – Technology, AI, Digital Solutions – Healthcare
Associate Director leading healthcare technology, AI, and digital transformation engagements for BRG’s healthcare advisory practice. Translating client priorities into technology roadmaps and scalable solutions.
AI Strategist
AI Strategist helping retail and consumer brands identify operational opportunities and deploy applied AI systems. Owning client relationships, business cases, delivery direction, and measurable outcomes across Latin America.
AI Strategist
AI Strategist helping WON redesign retail and consumer business operations with applied AI. Owning client discovery, business cases, delivery direction, and measurable outcomes.
Senior AI Agent Engineer
Senior AI Agent Engineer building Rumor Avenue's new AI product from scratch. Developing Python/FastAPI backend, React interfaces, and production LLM features.
AI Safety Expert, English – Kannada
AI safety red-teaming specialist probing frontier models for Mercor. Generating adversarial test data, vulnerability analyses, and reproducible attack artifacts for AI labs and enterprises.
AI Safety Expert, English, Punjabi
AI safety red teamer probing Mercor-trained AI models through adversarial English and Punjabi testing. Generating vulnerability annotations, attack cases, datasets, and reproducible reports.
AI Safety Expert – English, Odia
AI safety expert red-teaming Mercor’s frontier AI models through adversarial testing and human-data generation. Evaluating vulnerabilities in English and Odia across flexible, fully remote contract projects.