{"schemaVersion":"jobsearcher.job.v1","id":"ca66d06263e4e2523e83eab6","url":"https://jobsearcher.com/jobs/ca66d06263e4e2523e83eab6","canonicalUrl":"https://jobsearcher.com/jobs/ca66d06263e4e2523e83eab6","title":"Staff Security Engineer - AI","description":"OverviewIn this role you will own the security of Compass's AI-enabled products, shaping the multi-year strategy to secure AI capabilities across the platform. You will collaborate with AI platform and product teams to unify security standards, perform threat modeling, and deploy real-time protections for AI inputs/outputs. Your work will reduce risk in RAG pipelines, agent workflows, and retrieval systems, while guiding executives on AI risk and engineering roadmaps. This role combines security, AI, and platform-scale impact in a fast-growing tech organization.Compensation / Benefitsmedical, dental and vision benefits401(k) planpaid vacation and holidaysparenteral leave and recharge leaveflexible spending accounts (FSAs)equity or incentive programsResponsibilitiesOwn the AI product security roadmap and define vision and standards with AI platform and product engineering teamsThreat model AI capability builds, conduct architectural reviews for AI features, RAG pipelines, multi-agent workflows, and automated decisioningBuild production guardrails for LLM inputs/outputs: injection mitigation, jailbreak defense, output verification and data egress checksDesign blast-radius controls for autonomous agents: permissions, human-in-the-loop, audit trails, safe tool invocationSecure the retrieval layer: access controls, source integrity, tenancy boundaries, and retrieval protections across RAG/vector storesHarden the AI supply chain: assess posture, privacy controls, data retention, and terms with third-party models/providersInstrument and detect AI abuse in production: telemetry for tool invocation, prompt abuse, data exfiltration; integrate with monitoringAutomate secure AI patterns: reusable libraries, CI/CD checks, evaluation harnessesAdvise and evangelize: translate AI risk into engineering roadmaps for engineers and executivesKey requirements7+ years in security engineering with 2+ years in AI/ML or LLM securityEnd-to-end security of production AI/ML systems including lifecycle and runtimeExperience with adversarial ML and LLM risks; hands-on red teamingStrong application and cloud security fundamentals (AWS and/or GCP, Kubernetes, IAM, API security, DevSecOps)Experience threat modeling complex distributed systems and remediating with engineering teamsStrong strategic communication skills translating AI risk into business impactProactive and solution-oriented mindsetClear cross-functional communicationCapability to translate complex AI risk into actionable roadmapsPython or Go production codingExperience building security pipelines and integrations for AI/ML workloadsThreat modeling and secure-by-default AI patterns","company":"Compass","rawCompany":"compass","city":"Springfield","state":"IL","isRemote":false,"isActive":false,"createdAt":"2026-10-26T13:33:07.774Z","occupations":[{"code":"15-1299.05","title":"Information Security Engineers","slug":"information-security-engineers"},{"code":"15-1212.00","title":"Information Security Analysts","slug":"information-security-analysts"},{"code":"13-1199.07","title":"Security Management Specialists","slug":"security-management-specialists"}],"industries":[{"code":"541512","title":"Computer Systems Design Services","slug":"computer-systems-design-services"},{"code":"513210","title":"Software Publishers","slug":"software-publishers"},{"code":"541511","title":"Custom Computer Programming Services","slug":"custom-computer-programming-services"}],"jobPosting":{"@context":"https://schema.org","@type":"JobPosting","title":"Staff Security Engineer - AI","description":"OverviewIn this role you will own the security of Compass's AI-enabled products, shaping the multi-year strategy to secure AI capabilities across the platform. You will collaborate with AI platform and product teams to unify security standards, perform threat modeling, and deploy real-time protections for AI inputs/outputs. Your work will reduce risk in RAG pipelines, agent workflows, and retrieval systems, while guiding executives on AI risk and engineering roadmaps. This role combines security, AI, and platform-scale impact in a fast-growing tech organization.Compensation / Benefitsmedical, dental and vision benefits401(k) planpaid vacation and holidaysparenteral leave and recharge leaveflexible spending accounts (FSAs)equity or incentive programsResponsibilitiesOwn the AI product security roadmap and define vision and standards with AI platform and product engineering teamsThreat model AI capability builds, conduct architectural reviews for AI features, RAG pipelines, multi-agent workflows, and automated decisioningBuild production guardrails for LLM inputs/outputs: injection mitigation, jailbreak defense, output verification and data egress checksDesign blast-radius controls for autonomous agents: permissions, human-in-the-loop, audit trails, safe tool invocationSecure the retrieval layer: access controls, source integrity, tenancy boundaries, and retrieval protections across RAG/vector storesHarden the AI supply chain: assess posture, privacy controls, data retention, and terms with third-party models/providersInstrument and detect AI abuse in production: telemetry for tool invocation, prompt abuse, data exfiltration; integrate with monitoringAutomate secure AI patterns: reusable libraries, CI/CD checks, evaluation harnessesAdvise and evangelize: translate AI risk into engineering roadmaps for engineers and executivesKey requirements7+ years in security engineering with 2+ years in AI/ML or LLM securityEnd-to-end security of production AI/ML systems including lifecycle and runtimeExperience with adversarial ML and LLM risks; hands-on red teamingStrong application and cloud security fundamentals (AWS and/or GCP, Kubernetes, IAM, API security, DevSecOps)Experience threat modeling complex distributed systems and remediating with engineering teamsStrong strategic communication skills translating AI risk into business impactProactive and solution-oriented mindsetClear cross-functional communicationCapability to translate complex AI risk into actionable roadmapsPython or Go production codingExperience building security pipelines and integrations for AI/ML workloadsThreat modeling and secure-by-default AI patterns","datePosted":"2026-10-26T13:33:07.774Z","dateModified":"2026-10-26T13:33:07.774Z","hiringOrganization":{"@type":"Organization","name":"Compass","sameAs":"https://jobsearcher.com"},"jobLocation":{"@type":"Place","address":{"@type":"PostalAddress","addressLocality":"Springfield","addressRegion":"IL","addressCountry":"US"}},"identifier":{"@type":"PropertyValue","name":"JobSearcher","value":"ca66d06263e4e2523e83eab6"},"url":"https://jobsearcher.com/jobs/ca66d06263e4e2523e83eab6"}}