可信智能体高级研究员-安全与风控
Core
Research and build end-to-end security and risk control systems for AI agents, covering decision-making, tool invocation, memory management, and multi-agent collaboration.
Role type
Senior Research Scientist (AI Agent Security)
Builds
Runtime security engines, safety platforms, and operational tracing systems for AI agents.
Domain
Artificial Intelligence / Cybersecurity
Deliverable
production ML models
Required skills
Threat modeling, prompt injection defense, anomaly detection, adversarial sample protection, data leak prevention, zero trust architecture, Transformer mechanisms, Python, Go, LangChain, LlamaIndex, AutoGPT, Prompt Engineering, Context Engineering.
Preferred skills
Building security systems from 0 to 1, publishing high-level papers in AI security, contributing to open-source AI security frameworks.
Responsibilities
Design and implement runtime security engines to intercept malicious tool calls and detect abnormal behaviors; build a security operations loop for real-time monitoring and automatic incident response; develop general security components to support company-wide agent product integration; participate in industry standard setting for agent safety.
Seniority
Senior, hands-on IC