内部风险Agent算法工程师/专家 - 安全与风控
Core
Design and implement a multi-Agent collaborative framework for internal threat detection, automated investigation, and strategy evolution within a zero-trust security system.
Role type
Senior IC AI Agent algorithm engineer (security & risk control)
Builds
Multi-Agent systems for attack simulation, alert triage, evidence orchestration, and automated strategy iteration.
Domain
Cybersecurity, Internal Threat Detection, AI Agents
Deliverable
production ML models
Required skills
Multi-Agent system design, LLM application development, Prompt engineering, Python, Adversarial sample generation, Threat hunting, Automated alert triage, Tool orchestration
Preferred skills
Red teaming experience, Model fine-tuning, Agentic SoC/SOAR construction, DLP/UEBA expertise
Technologies
Python, LLMs, Agent frameworks, DLP, UEBA, Threat hunting tools
Responsibilities
Design multi-Agent frameworks for detection and repair; Generate adversarial samples for robustness testing; Optimize detection rules and thresholds via negative case analysis; Automate alert triage and evidence summarization; Build automated investigation pipelines and metric systems.
Seniority
Senior, hands-on IC
