AI安全验证技术专家
Core
Lead full-lifecycle security validation for product AI features, including system analysis, threat modeling, vulnerability research, and model attack/defense studies.
Role type
Senior AI Security Validation Engineer (LLM & AI Agents)
Builds
AI security assessment reports, security toolchains, and defense mechanisms for AI models and agents.
Domain
Artificial Intelligence / Cybersecurity
Deliverable
production ML models
Required skills
AI model security, adversarial sample defense, AI agent security, vulnerability exploitation, threat analysis, LLM training data synthesis, fine-tuning, reinforcement learning, traditional network security testing
Preferred skills
Published research at top-tier conferences, enterprise AI4Sec implementation, security development LLM projects
Technologies
LLMs, AI agents, security toolchains, adversarial testing frameworks
Responsibilities
Conduct threat analysis and vulnerability research for AI systems; develop and optimize AI security validation frameworks and standards; research and implement cutting-edge AI security technologies.
Seniority
Senior, hands-on IC
