大模型评测研究员（智能安全） - 安全与风控
Core
Research and evaluate large model security applications, including vulnerability mining and penetration testing, to define new security tasks and benchmarks.
Role type
Senior Research Scientist (Large Model Security Evaluation)
Builds
Security benchmarks, evaluation pipelines, and security products for large models.
Domain
Artificial Intelligence / Cybersecurity
Deliverable
production ML models
Required skills
Large model security, vulnerability mining, penetration testing, benchmark design, code implementation, cross-team collaboration
Preferred skills
Leading influential projects or publishing papers in large model or AI security, experience with CTF/reverse engineering/model training/Agents design
Technologies
Large language models, Agents, security frameworks
Responsibilities
Research large model security application effects, define new security task capabilities, build evaluation processes, analyze evaluation results with model training and security teams
Seniority
Senior, hands-on IC