Tasks:
- * Build AI Agent-driven automated security testing systems
- * Build AI-versus-AI automated attack and defense platforms
- * Develop quantitative AI security benchmarking frameworks
- * Establish evaluation-feedback-training loops with model teams
- * Optimize security capabilities using evaluation data
Perks/Benefits:
Skills/Tech stack required:
[AFL] [Agent Development] [AI Agent] [AI Agent Development] [Automated security] [Automated security testing] [Binary Vulnerability Research] [C#] [C++] [Code auditing] [CodeQL] [Context Management] [Exploit Development] [Fuzzing] [Joern] [LibFuzzer] [LLM-assisted vulnerability discovery] [Multi-step reasoning] [Multi-step reasoning orchestration] [Penetration Testing] [Python] [Red Teaming] [Reverse debugging] [Security benchmarking] [Security Testing] [Security tool development] [Semgrep] [Syzkaller] [Tool Development] [Tool use] [Vulnerability discovery] [Vulnerability research]
Educational requirements:
N/A
Role(s):
[AI Red Team Security Engineer] [Engineer] [Red Team Security Engineer] [Security Engineer]