Security Engineer

About the job Mercor connects elite creative and technical talent with leading AI research labs. Headquartered in San Francisco, our investors include Benchmark , General Catalyst , Peter Thiel , Adam D'Angelo , Larry Summers , and Jack Dorsey . Position: Red Team Specialist Type: Full-time or Part-time Contract Work Compensation: $29/hour Location: Remote ; Geography restricted to USA, Brazil Role Responsibilities Evaluate conversational AI models for vulnerabilities through jailbreaks, prompt injections, and misuse cases. Generate high-quality human data by annotating failures, classifying vulnerabilities, and flagging systemic risks. Apply structure by following taxonomies, benchmarks, and playbooks to maintain consistent testing. Document reproducibly by producing reports, datasets, and attack cases that customers can act on. Work independently and asynchronously to meet deadlines while improving AI model performance . Qualifications Must-Have Prior experience in red teaming (AI adversarial work, cybersecurity, socio-technical probing). Native-level fluency in English and Brazilian Portuguese . Strong communication skills to explain risks clearly to technical and non-technical stakeholders. Preferred Experience in Adversarial ML (jailbreak datasets, prompt injection, RLHF/DPO attacks, model extraction). Background in Cybersecurity (penetration testing, exploit development, reverse engineering). Expertise in Socio-technical risk (harassment/disinfo probing, abuse analysis, conversational AI testing). Compensation & Legal Hourly contractor , Paid weekly . Application Process (Takes 20–30 mins to complete) Upload resume AI interview based on your resume Submit form Resources & Support For details about the interview process and platform information, please check: https://talent.docs.mercor.com/welcome/welcome For any help or support, reach out to: support@mercor.com PS: Our team reviews applications daily. Please complete your AI interview and application steps to be considered for this opportunity.