AI Agent安全工程师/专家-智能安全
Core
Lead security governance for internal AI usage across all scenarios, including third-party models, AI Agents, and office AI, implementing control schemes and fixing risks to support compliant business innovation.
Role type
Senior AI Security Engineer / Expert
Builds
Security control schemes for third-party models and AI Agents; data desensitization, risk detection, behavior auditing, and warning interception capabilities.
Domain
Internet Security / AI Safety
Deliverable
production ML models | infrastructure
Required skills
AI security governance, third-party model security, AI Agent security, data desensitization, risk detection, behavior auditing, warning interception, security assessment, compliance auditing, threat research, LLM protection, security development, attack/defense.
Preferred skills
Enterprise AI security governance, LLM risk control, Agent security protection, DLP, security auditing, permission control.
Responsibilities
Implement AI security governance schemes for third-party models and AI Agents; build technical capabilities for data desensitization, risk detection, and auditing; conduct security assessments and compliance inspections for internal AI products and third-party model access; track AI security frontier technologies and research defense solutions for large models and agents.
Seniority
Senior, hands-on IC