[Remote] AI Information Security Engineer

Note: The job is a remote job and is open to candidates in USA. Southern New Hampshire University is a team of innovators committed to transforming lives through education. They are seeking an AI Information Security Engineer to secure AI systems and models by implementing security measures and collaborating with various teams to ensure safety and compliance in production environments.ResponsibilitiesDocument AI system components and data flows, including prompts, context, embeddings, training data, model artifacts, outputs, and agent tool interactionsIn collaboration with the AI team, identify attack surfaces, trust boundaries, and privilege transitions within AI pipelines and agent workflows and perform structured threat modeling for AI systems during design, development, and change cycles in collaboration with the AI teamIn collaboration with the AI team, translate identified threats into concrete, relevant security requirements and engineering tasks in collaboration with the AI teamImplement technical controls informed by established AI security frameworks (e.g., OWASP LLM Top 10, NIST AI RMF) according to compliance requirements and AI governance guidanceDesign, build, and maintain automated security testing for AI systems within CI/CD pipelines, supports testing for prompt injection, unsafe model behavior, misconfigured access, data exposure, and agent misuse. Ensure AI security controls are validated during build, deployment, and change cycles, with failures surfaced early to engineering teamsImplement technical guardrails to protect sensitive data used by AI systems, including retrieval of augmented generation (RAG) pipelines and external data sourcesIn collaboration with the AI Team, Design and operate controls for sensitive data identification, minimization, redaction, and leakage prevention—addressing PII and other protected data in prompts, context, embeddings, and outputs to ensure privacy preserving AI operation in production environmentsDesign, implement, and maintain security controls across the full AI/ML lifecycle—including data ingestion, training, evaluation, deployment, inference, and CI/CD—covering model artifacts, configurations, embeddings, prompts, and deployment patternsImplement and operate runtime safeguards for AI services and agent-based systems, including input and output controls, context isolation, tool use restrictions, and abuse prevention mechanisms (e.g., rate limiting and anomaly detection), ensuring safe operation without breaking functional requirementsDesign security controls that balance safety, system performance, reliability, and developer usability in production of AI servicesImplement and operate secure identity, secrets, and access control patterns for AI services, agents, and integrations, enforcing least privilege, integrating with enterprise IAM and key management systems, and monitoring credential usage and rotationInstrument AI systems to produce actionable logging, metrics, and traces; build dashboards and alerts for detecting prompt manipulation, anomalous usage, and unexpected behavior; and integrate AI specific signals into enterprise security operations workflowsEmbed with AI engineering and platform teams to design and maintain technical security controls; develop reusable security components and patterns; contribute documentation and runbooks; and, in collaboration with the AI team, communicate AI security requirements and remediation outcomes to technical, non-technical, and cross functional stakeholdersSkills5+ years of experience in IT or cybersecurity, with engineering responsibilities (i.e. IT Security or Application Development)2 + years of experience securing AI/ML systems or adjacent domains with demonstrated application to AI workloadsExperience with security engineering principles, including authentication, authorization, logging, and monitoringExperience with AI/ML concepts such as models, training data, inference pipelines, embeddings, and agent frameworksExperience modeling data flows, trust boundaries, and attack paths in AI systemsExperience mitigating threats such as prompt injection, model poisoning, model theft, and data leakageExperience implementing controls such as input validation, output filtering, context isolation, and abuse detectionBenefitsHigh-quality, low-deductible medical insuranceLow to no-cost dental and vision plans5 weeks of paid time off (plus almost a dozen paid holidays)Employer-funded retirementFree tuition programParental leaveMental health and wellbeing resourcesCompany OverviewFounded in 1932, Southern New Hampshire University has grown from a small school of accounting and secretarial science into one of the nation’s largest nonprofit, accredited universities. It was founded in 1932, and is headquartered in Manchester, NH, US, with a workforce of 10001+ employees. Its website is http://www.snhu.edu.