AI Security Researcher

Cisco•San Francisco, CA

About The Position

Cisco’s AI Software & Platform Group develops generative AI applications, enterprise AI platforms, and developer tools. The AI Threat Intelligence and Security Research team investigates emerging threats to foundation models, agentic workflows, and distributed AI platforms and supply chains, and translates research into practical protections such as red teaming, security tools, threat detections, provenance capabilities, runtime guardrails, and product innovations. The team also contributes through open-source projects, industry frameworks, technical publications, customer and partner engagement, and education. The AI Security Researcher will serve as a technical lead in adversarial research and agentic security detection frameworks. The role partners with Engineering, Product Management, and Applied AI teams to deliver security features for Cisco platforms and the broader security community. Responsibilities span researching adversarial attacks, architecting agentic security frameworks, deploying threat detection and real-time guardrails, conducting red-team testing, and translating research findings into production capabilities and executive risk briefings.

Requirements

  • Bachelor’s degree and 12+ years of related experience, Master’s degree and 8+ years of related experience, or PhD and 5+ years of related experience, or equivalent related work experience.
  • At least 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-exfiltration vectors, and mapping threats and controls to frameworks such as the 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.

Nice To Haves

  • Experience researching or securing autonomous agent frameworks, tool integrations, and open standards such as Model Context Protocol (MCP), LangChain, or LlamaIndex.
  • A 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 such as NeMo Guardrails or Llama Guard.
  • Experience with cloud-scale data infrastructure such as Snowflake, Spark, or 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.

Responsibilities

  • Lead research into adversarial attacks targeting generative AI and agentic systems, including prompt injection, jailbreaking, agent goal drift or misalignment, backdoors, model data poisoning, model evasion, and malicious tool-calling exploitation.
  • Architect agentic security frameworks and defense-in-depth guardrails for open agent protocols such as MCP, multi-agent orchestration, and autonomous execution environments.
  • Design, evaluate, and deploy automated threat detection models, behavioral telemetry signatures, and real-time inference guardrails in enterprise production platforms.
  • Design, conduct, evaluate, and iterate on adversarial red-teaming and safety benchmarking across foundation models, fine-tuned LLMs, and RAG pipelines, mapping findings to the MITRE ATLAS matrix.
  • Partner with Product Management and core Engineering teams to turn AI/ML security findings into production-ready platform capabilities and executive risk briefings.

Benefits

  • Medical insurance
  • Dental insurance
  • Vision insurance
  • 401(k) plan with Cisco matching contribution
  • Paid parental leave
  • Short- and long-term disability coverage
  • Basic life insurance
  • Paid holidays
  • Floating holiday for non-exempt employees
  • Paid day off for employee’s birthday
  • Paid year-end holiday shutdown
  • Personal wellness days
  • Paid vacation time for non-exempt employees
  • Flexible vacation time off program for eligible exempt employees
  • Sick time off
  • Additional paid time away may be requested for critical or emergency family issues
  • Optional paid volunteer days
  • Annual bonuses for eligible non-sales roles
  • Performance-based incentive pay for employees on sales plans
  • Employees may be eligible for Cisco restricted stock unit grants
© 2026 Teal Labs, Inc
Privacy PolicyTerms of Service