AI Security Engineer

Key Responsibilities: Secure the AI and ML lifecycleDefine security requirements for model development, training, evaluation, deployment, and monitoringThreat model AI systems and AI features in products, including abuse cases and misuse scenariosEstablish secure-by-design patterns for model endpoints, prompts, RAG pipelines, and agent workflowsValidate controls for model access, rate limiting, tenant isolation, and secrets managementProtect data used by AIClassify and control training data, fine-tuning data, prompts, and retrieved contextImplement guardrails for sensitive data exposure, including PII and PCI dataDefine retention, deletion, and lineage requirements for AI datasets and outputsPartner with Privacy and Legal on data handling, regulatory expectations, and third-party data useSecure AI infrastructure and supply chainHarden AI platforms, GPU and container workloads, model registries, and artifact storesAssess risks in third-party models, libraries, embeddings, and model hosting servicesDefine integrity controls for model artifacts, evaluation sets, and pipeline automationBuild CI and CD checks for AI assets, including scanning, signing, and policy enforcementDetection, monitoring, and response for AI threatsBuild logging standards for model requests, responses, tool calls, and retrieval eventsCreate detections for prompt injection, data exfiltration attempts, model extraction signals, and anomalous usageDevelop incident response playbooks for AI events, including containment and rollback plansRun security testing for AI features, including red teaming and structured adversarial testingGovernance and program deliveryCreate practical AI security standards, patterns, and reference architecturesDefine KPIs such as reduction in sensitive output leakage, time to detect misuse, and policy coverageLead risk reviews for new AI features and vendor assessments for AI servicesTrain engineering and data science teams on secure AI patterns and common attack pathsTools and Technologies You Might UseCloud: AWS, Azure, GCPContainers: Kubernetes, DockerDevSecOps: GitHub Actions, GitLab CI, Azure DevOps, TerraformSecurity: SIEM, EDR, WAF, API gateways, secrets managersAI stack: model gateways, vector databases, model registries, ML pipelinesExamples of Work and Technical ScopeSecure an LLM gateway with authentication, authorization, quotas, content filtering, and audit loggingAdd prompt injection defenses for an agent that uses tools like web search and internal APIsImplement retrieval filtering, context redaction, and output scanning for a RAG applicationBuild model artifact signing and verification into the release pipelineCreate detections in SIEM for abnormal model usage, including model scraping patternsRequired Qualifications 8 years of experience in Information Security, but 5+ years in security engineering, application security, cloud security, or detection engineering if there is no degreeAt least 3 years of experience in AI SecurityExperience securing LLM-based applications, RAG systems, or agentic workflowsFamiliarity with adversarial ML concepts, such as prompt injection, model inversion, and model extractionExperience with one or more cloud platforms, AWS, Azure, or GCPHands-on experience with at least one programming language, Python preferredStrong understanding of AI, LLMs, API security, identity, secrets management, and cloud controlsExperience building security controls into CI and CD pipelinesProven ability to lead cross-functional security work with engineering and product teamsEffectively communicate complex technical concepts to both technical and non-technical stakeholdersEffectively communicate to leadership and know when to escalate with proactive, clear, data-driven insight, highlighting risks, roadblocks, and solutionsProven leadership capabilities with the ability to influence and drive change