Member of Technical Staff (Senior AI Security Researcher)
Core
Lead applied research on adversarial AI agents and coordinated multi-agent or swarm-like behavior, developing methods to detect, attribute, interrupt, and contain offensive agent swarms.
Role type
Senior IC AI security researcher (adversarial multi-agent systems)
Builds
Instrumented environments for observing agent coordination, reproducible evaluation assets, and security guidance for red-team and defense partners
Domain
AI security, adversarial machine learning, multi-agent systems
Deliverable
production ML models
Required skills
Python, machine learning frameworks, adversarial AI research, multi-agent coordination analysis, behavioral signature characterization, provenance tracking, threat detection, security experiment design, simulation design, research project leadership
Preferred skills
Peer-reviewed publications in agentic AI security, patents in adversarial ML, released research software, experience with behavioral analysis and attribution methods
Technologies
Python, machine learning frameworks
Responsibilities
Characterize coordination patterns and behavioral signatures across agent populations, develop methods to detect and contain coordinated offensive agent swarms, stress-test detection methods across changing models and topologies, design instrumented security experiments and simulations, produce reproducible evaluation assets and security guidance
Seniority
Senior, hands-on IC
