CareerPlanSign in

数据安全蓝军-安全与风控

北京💼 Full-time🗓 2026-09-28

Core

Red teaming AI Agents and LLM applications through full-link attack-defense drills to identify security threats and optimize defense strategies.

Role type

Senior IC AI security researcher (red team)

Builds

Automated attack toolchains, POCs, and reusable attack methodologies for AI Agents and LLMs

Domain

AI/ML security, Large Language Models, Cybersecurity

Deliverable

production ML models

Required skills

LLM and AI Agent architecture understanding, penetration testing, Python, Golang/Java/C++, vulnerability analysis, attack chain design

Preferred skills

0-day vulnerability discovery, public security research publications, CTF/HW competition experience

Technologies

LLM, RAG, MCP, ATT&CK, Python, Golang, Java, C/C++

Sourced via bytedance · Listed on CareerPlan, which tracks 855,000+ jobs from 20+ sources.