Cisco Technical Lead Threat Intelligence 

United States, Georgia, Atlanta 

266413323

are accepted until further notice.

As a Lead Researcher, you will play a pivotal role in investigating, analyzing and mitigating emerging threats targeting AI / ML. You will work closely with the Director of AI Threat Intelligence to build a world-class AI threat research capability, delivering actionable intelligence, advancing the state of AI security research, and helping secure Cisco’s AI-driven products and services. You will collaborate with fellow researchers, data scientists, security engineers, and product teams to proactively identify AI-related risks, with a strong focus on securing autonomous AI agents.

• Lead research into AI/ML-specific threats, including adversarial attacks, prompt injection, model exploitation, data poisoning, model evasion, tool misuse and misuse of generative AI systems.
• Conduct threat modeling of AI agents and multi-agent systems, including Model Context Protocols (MCP), A2A — ensuring safe transmission and handling of context, memory, and system metadata across model calls and between AI Agents.
• Track evolving threat actor tactics, techniques, and procedures (TTPs) targeting AI/ML ecosystems, particularly those exploiting agentic behavior and context management flaws.
• Produce and publish high-quality, actionable threat intelligence reports, technical analysis papers, and internal briefings to inform engineering, product, and executive teams.
• Represent Cisco in external research communities, conferences, working groups, and standards organizations where AI security and threat intelligence are advancing.
• Mentor junior researchers and contribute to building a center of excellence around AI threat intelligence and adversarial research.

• 8+ years of experience in cybersecurity threat intelligence, adversarial research, red teaming, or offensive security, with exposure to AI/ML systems preferred.
• Strong expertise in AI/ML technologies, particularly generative models, AI agent frameworks, memory-augmented AI, and Model Context Protocol (MCP) designs.
• Hands-on experience analyzing vulnerabilities in AI systems, including prompt injections, agentic exploits, and context/memory transmission flaws.
• Proficiency in Python or similar scripting languages for prototyping, simulation, and analysis.
• Familiarity with threat frameworks such as MITRE ATLAS, ATT&CK for AI, or emerging AI-specific threat models.

• Record of contributions to AI security research communities (publications, CVEs, conference presentations, open-source projects, blogs).
• Knowledge of responsible AI practices, secure, safe deployment of autonomous and agentic AI systems.
• Familiarity with securing agent-to-agent communication protocols, and external tool orchestration in multi-agent environments.
• Experience working with AI/ML pipelines in cloud environments (AWS, Azure, GCP).