{"schemaVersion":"jobsearcher.job.v1","id":"a9b9a1341ee1d4e68e3b4bc7","url":"https://jobsearcher.com/jobs/a9b9a1341ee1d4e68e3b4bc7","canonicalUrl":"https://jobsearcher.com/jobs/a9b9a1341ee1d4e68e3b4bc7","title":"Secure Code Review AI Evaluator","description":"Secure Code Review AI Evaluator is a remote red-team track for stress-testing AI systems against adversarial prompts. Reviewers craft attack scenarios, document the failure mode, and pair each successful jailbreak with the rubric clause it violated so the safety team can patch the gap.\nWhy this role matters\nAdversarial evaluation is how AuraOne hardens AI models before they ship to customers. Reviewers think like attackers and write up failures with enough rigor that the modeling team can reproduce, fix, and regress-test them.\nResponsibilities\nDesign adversarial prompts that probe known weakness classes (jailbreak, policy bypass, prompt injection) for Secure Code Review AI Evaluator assignments.\nDocument every successful attack with reproduction steps and the policy clause it violated.\nScore model defenses across single-turn and multi-turn conversations.\nTriage emerging attack vectors and route them to the safety team with severity ratings.\nMaintain a personal library of attack patterns and propose new red-team rubrics.\nCalibrate against the broader red-team cohort to keep coverage and severity consistent.\nQualifications\nDemonstrated experience red-teaming AI systems, security research, or adversarial ML work for Secure Code Review AI Evaluator work.\nStrong written communication — your reports become the patch ticket.\nComfort working in policy-grey areas with clear documentation of what was attempted and why.\nFamiliarity with prompt-injection, jailbreak, and policy-bypass taxonomies.\nReliable async availability for at least 10 hours per week.\nExample tasks\nConstruct a 5-turn adversarial conversation that bypasses a specific policy clause and write up the patch ticket.\nScore a model's defenses against a known jailbreak pattern across 20 variants.\nPropose a new red-team rubric category after spotting an emerging attack vector.\nReproduce a failure another reviewer reported and confirm the severity tag.\nNice to have\nBackground in offensive security, AppSec, or trust & safety operations.\nExperience publishing or reproducing public adversarial-ML research.\nMultilingual fluency for cross-language attack testing.\nSkills\nAdversarial prompting\nRed-team analysis\nPolicy taxonomy\nFailure documentation\nSecure Code Review AI evaluation\nCybersecurity\nAI evaluation\nRubric writing\nExpert review\nWork model\nRemote — US-eligible. Remote · Independent specialist contractor. Employment type: CONTRACTOR. Applicants must be authorized to work from US.\nCompensation\nHourly rate confirmed after the interview process.\nApplication process\nApply through AuraOne's specialist intake for role-specific routing and review. Final project scope, schedule, and contractor terms are confirmed before placement.","company":"Auraone Human Data","rawCompany":"auraone human data","city":"Remote","state":"OR","isRemote":false,"isActive":false,"createdAt":"2026-08-05T15:44:01.911Z","occupations":[{"code":"15-1212.00","title":"Information Security Analysts","slug":"information-security-analysts"},{"code":"15-1252.00","title":"Software Developers","slug":"software-developers"},{"code":"15-1299.04","title":"Penetration Testers","slug":"penetration-testers"}],"industries":[{"code":"541511","title":"Custom Computer Programming Services","slug":"custom-computer-programming-services"},{"code":"541512","title":"Computer Systems Design Services","slug":"computer-systems-design-services"},{"code":"513210","title":"Software Publishers","slug":"software-publishers"}],"jobPosting":{"@context":"https://schema.org","@type":"JobPosting","title":"Secure Code Review AI Evaluator","description":"Secure Code Review AI Evaluator is a remote red-team track for stress-testing AI systems against adversarial prompts. Reviewers craft attack scenarios, document the failure mode, and pair each successful jailbreak with the rubric clause it violated so the safety team can patch the gap.\nWhy this role matters\nAdversarial evaluation is how AuraOne hardens AI models before they ship to customers. Reviewers think like attackers and write up failures with enough rigor that the modeling team can reproduce, fix, and regress-test them.\nResponsibilities\nDesign adversarial prompts that probe known weakness classes (jailbreak, policy bypass, prompt injection) for Secure Code Review AI Evaluator assignments.\nDocument every successful attack with reproduction steps and the policy clause it violated.\nScore model defenses across single-turn and multi-turn conversations.\nTriage emerging attack vectors and route them to the safety team with severity ratings.\nMaintain a personal library of attack patterns and propose new red-team rubrics.\nCalibrate against the broader red-team cohort to keep coverage and severity consistent.\nQualifications\nDemonstrated experience red-teaming AI systems, security research, or adversarial ML work for Secure Code Review AI Evaluator work.\nStrong written communication — your reports become the patch ticket.\nComfort working in policy-grey areas with clear documentation of what was attempted and why.\nFamiliarity with prompt-injection, jailbreak, and policy-bypass taxonomies.\nReliable async availability for at least 10 hours per week.\nExample tasks\nConstruct a 5-turn adversarial conversation that bypasses a specific policy clause and write up the patch ticket.\nScore a model's defenses against a known jailbreak pattern across 20 variants.\nPropose a new red-team rubric category after spotting an emerging attack vector.\nReproduce a failure another reviewer reported and confirm the severity tag.\nNice to have\nBackground in offensive security, AppSec, or trust & safety operations.\nExperience publishing or reproducing public adversarial-ML research.\nMultilingual fluency for cross-language attack testing.\nSkills\nAdversarial prompting\nRed-team analysis\nPolicy taxonomy\nFailure documentation\nSecure Code Review AI evaluation\nCybersecurity\nAI evaluation\nRubric writing\nExpert review\nWork model\nRemote — US-eligible. Remote · Independent specialist contractor. Employment type: CONTRACTOR. Applicants must be authorized to work from US.\nCompensation\nHourly rate confirmed after the interview process.\nApplication process\nApply through AuraOne's specialist intake for role-specific routing and review. Final project scope, schedule, and contractor terms are confirmed before placement.","datePosted":"2026-08-05T15:44:01.911Z","dateModified":"2026-08-05T15:44:01.911Z","hiringOrganization":{"@type":"Organization","name":"Auraone Human Data","sameAs":"https://jobsearcher.com"},"jobLocation":{"@type":"Place","address":{"@type":"PostalAddress","addressLocality":"Remote","addressRegion":"OR","addressCountry":"US"}},"identifier":{"@type":"PropertyValue","name":"JobSearcher","value":"a9b9a1341ee1d4e68e3b4bc7"},"url":"https://jobsearcher.com/jobs/a9b9a1341ee1d4e68e3b4bc7"}}