Red Team Consultant, Platform Responsibility
Core
Lead adversarial testing of global content security systems to identify vulnerabilities and improve content safety across cultural and linguistic contexts.
Role type
Senior IC Red Team Consultant (AI/ML Security)
Builds
Adversarial sample pipelines, LLM-powered agent systems for automation, and threat pattern frameworks
Domain
Content Security / Trust & Safety / AI Security
Deliverable
production ML models
Required skills
Threat discovery and risk analysis, Adversarial sample construction, Adversarial evaluation and remediation, AI agent development, LLM workflow design, Prompt engineering, Cross-functional program management
Preferred skills
Adversarial attack techniques against ML systems (evasion, prompt injection), Threat intelligence and OSINT, International content security regulations
Technologies
LLMs, AI Agents, Threat Intelligence Tools
Responsibilities
Lead structured threat pattern discovery from multiple signal sources; Build end-to-end adversarial sample construction pipelines; Design and execute adversarial evaluation programs; Lead design and deployment of LLM-powered agent systems for Red Team operations