AI安全蓝军高级工程师
Core
Conduct security assessments and adversarial exercises for core business and AI scenarios, focusing on discovering risks in LLMs, AI Agents, and infrastructure.
Role type
Senior AI Security Engineer (Red/Blue Team)
Builds
Automated security capabilities, vulnerability discovery tools, and risk validation frameworks for AI systems.
Domain
Cybersecurity + Artificial Intelligence (LLMs, Agents)
Deliverable
production ML models
Required skills
Vulnerability research, penetration testing, Python/Go development, LLM security, Prompt Engineering, Tool Use, RAG, Multi-Agent systems, Risk analysis
Preferred skills
Experience with AI infrastructure supply chain security, Agent anomaly detection, Automated vulnerability discovery
Technologies
Python, Go, LLMs, Reasoning Models, MCP, Agent Skills
Responsibilities
Perform security assessments and adversarial exercises on AI scenarios; Research novel AI security risks (prompt injection, tool misuse, supply chain); Develop automated security capabilities using LLMs and Agents; Build AI security evaluation systems and benchmarks; Analyze new vulnerabilities and implement engineering solutions; Collaborate with business and technical teams to drive risk remediation.