AI隐私安全技术工程师-集团信息系统
Core
Systematically model and assess security risks for large model agent systems (tool calling, plugin integration, multi-step workflows) and design protective architectures.
Role type
Senior AI Privacy and Security Engineer (LLM/Agent)
Builds
Security benchmarks, red teaming frameworks, automated attack simulation tools, and engineering-grade safety components.
Domain
Artificial Intelligence / Large Language Models / Cybersecurity
Deliverable
production ML models
Required skills
LLM/Agent security research, threat modeling, prompt injection defense, jailbreak mitigation, adversarial testing, Python programming, red teaming
Preferred skills
Security governance, automated tool development, cross-functional collaboration
Technologies
Python, LLM frameworks, agent orchestration tools
Responsibilities
Model risk assessment and baseline establishment, security architecture design for input/output filtering and sandboxing, building standardized security benchmarks and red teaming frameworks, translating security research into engineering components.