Generative AI Security Engineer — Cloud & RAG

Cisco Systems, Inc.; North Carolina; On-site; USD 129,000 - 185,000; Full time

Benefits offered by this job

Medical, dental, vision insurance

401(k) with Cisco match

Paid parental leave

RSUs and stock grants

Job summary

Join Cisco's Enterprise AI team to build secure, scalable AI platforms enabling Generative AI-powered experiences across Cisco. You will design security controls for LLM-based systems, guard against prompt injection and data exfiltration, and harden RAG pipelines with strong access controls and monitoring.

You will work with platform and infra teams to secure deployment pipelines, perform threat modeling, and deploy automated detection of AI-specific risks across the enterprise.

Qualifications

• Bachelor's or Master's degree in Computer Science, Cybersecurity related field or equivalent certifications along with work experience.
• 3+ years of experience in application security, cloud security, or platform security engineering.
• Hands-on experience securing distributed systems or cloud-native applications (Kubernetes, APIs, microservices).
• Experience designing and implementing authentication, authorization, and data protection controls.
• Strong programming/scripting skills (Python, Go, or similar) for building security tooling and automation.

Responsibilities

• Design and implement security controls for Generative AI systems, including LLM-based applications, RAG pipelines, and agent-driven workflows.
• Identify and mitigate AI-specific threats such as prompt injection, data exfiltration, insecure tool usage, and model abuse.
• Establish guardrails for prompt handling, input/output validation, and safe tool invocation to ensure secure agent behavior.
• Secure Retrieval-Augmented Generation (RAG) pipelines by enforcing data access controls, source integrity, and retrieval boundary protections.
• Define and enforce model access controls, API protections, and runtime monitoring to prevent misuse and unauthorized access.
• Partner with AI platform and infrastructure teams to integrate security into model deployment pipelines and inference services.
• Conduct threat modeling and security assessments for AI systems, including model lifecycle, data pipelines, and inference endpoints.
• Build automated detection and response mechanisms for AI-specific risks, including anomalous queries and unsafe outputs.

Skills

Kubernetes

APIs

Microservices

Python

Go

Authentication

Authorization

Security tooling

Education

Bachelor's or Master's in Computer Science or Cybersecurity

Tools

Kubernetes

Cloud platforms

Security tooling

Threat modeling

Job description

Join Cisco's Enterprise AI team to build secure, scalable AI platforms enabling Generative AI-powered experiences across Cisco. You will design security controls for LLM-based systems, guard against prompt injection and data exfiltration, and harden RAG pipelines with strong access controls and monitoring.

You will work with platform and infra teams to secure deployment pipelines, perform threat modeling, and deploy automated detection of AI-specific risks across the enterprise.