The application window is expected to close on: 11/24/2026Your Impact
In this role, you will be a technical lead in adversarial research and agentic security detection frameworks, partnering across Engineering, Product Management, and Applied AI teams to deliver novel security features to Cisco's platforms and the broader security community.
• Lead Adversarial AI & Agentic Research: Lead research on adversarial charges targeting generative AI and agentic systems, including prompt injection, jail-breaking, agent goal drift or misalignment, backdoors, model data poisoning, model evasion, and malicious tool-calling exploitation.
• Architect Agentic Security Frameworks: Architect robust agentic security frameworks and defense-in-depth guardrails across open agent protocols (e.g., MCP), multi-agent orchestration, and autonomous execution environments.
• Deploy Threat Detection & Guardrails: Design, evaluate, and deploy automated threat detection models, behavioral telemetry signatures, and real-time inference guardrails into enterprise production platforms.
• Implement Advanced Adversarial Red-Teaming: Design, perform, evaluate, and iterate on sophisticated adversarial red-teaming and safety benchmarking across foundation models, fine-tuned LLMs, and Retrieval-Augmented Generation (RAG) pipelines, mapping findings to the MITRE ATLAS matrix.
• Drive multi-functional Production Security: Partner with product management and core engineering teams to translate sophisticated AI/ML security findings into production-ready platform capabilities and executive risk briefings.
Minimum Qualifications
• Bachelor's degree with 12+ years of related experience, Master's degree with 8+ years of related experience, or PhD with 5+ years of related experience, or equivalent related work experience.
• 5+ years of direct experience in AI/ML security research, adversarial machine learning, cyber threat intelligence and blue team operations (SOC, triage, vulnerability management, incident response), or foundation generative AI and supply chain model vulnerability analysis.
• Deep technical mastery of modern AI/ML concepts, adversarial AI/ML, detection engineering, and benchmarking/evaluation including transformer architectures, foundation models, fine-tuning, embeddings, evaluation harnesses, and RAG architectures.
• Experience analyzing and mitigating agentic security risks, prompt injection, jailbreaks, tool-calling vulnerabilities, or data ex-filtration vectors, and mapping threats and controls to frameworks such as Cisco AI Security & Safety Framework, MITRE ATLAS, and OWASP Top 10 for LLMs.
• Strong programming and prototyping experience in Python, Go, PyTorch/TensorFlow, and querying large-scale security datasets.
Preferred Qualifications
• Experience researching or securing autonomous agent frameworks, tool integrations, and open standards like Model Context Protocol (MCP), LangChain, or LlamaIndex.
• Prior experience with publication record, patent portfolio, or whitepapers in AI threat intelligence, AI safety, or AI red teaming (e.g., MITRE ATLAS, NeurIPS, IEEE, ACM).
• Experience developing custom LLM evaluation harnesses, automated red-teaming agents, or runtime guardrail systems (e.g., NeMo Guardrails, Llama Guard).
• Experience working with cloud-scale data infrastructure (Snowflake, Spark, Kafka) and deploying real-time security telemetry at enterprise scale.
• Experience configuring and maintaining Kubernetes deployments, Helm charts, and service scaling for containerized backend applications.