AI Researcher
Core
Analyze emerging AI threat vectors, build automated detections, and conduct adversarial testing to protect cloud-scale AI systems.
Role type
AI security researcher (threat intelligence & red teaming)
Builds
Automated detection pipelines, security frameworks, and open-source tools for Cisco Cloud Control
Domain
Cybersecurity + Generative AI
Required skills
AI threat intelligence, adversarial testing, red teaming, YARA rules, behavioral detections, OSINT investigations, prompt injection analysis, data poisoning assessment, model backdoor detection, Python, SQL
Preferred skills
Agentic AI architectures, Model Context Protocol, AI-assisted coding tools (Claude Code, Cursor), adversarial red/blue teaming, MITRE ATLAS, OWASP Top 10
Technologies
Snowflake, YARA, MITRE ATLAS, OWASP Top 10
Responsibilities
Conduct AI threat intelligence research to identify and profile malicious actors; Develop and maintain detection content for integration into customer-facing products; Research security risks across the AI lifecycle including prompt injection and data poisoning; Perform adversarial testing and red teaming across models and agentic deployments; Translate research into automated defense mechanisms; Analyze large-scale threat telemetry using modern data platforms
Seniority
Senior, hands-on IC
