OpenAI18.05.2026
Security Researcher, Agentic AI Threats
Зарплата не указана
Полная занятостьУдалёнка
Обязанности
- 01Identify paths by which capable future internal AI agents could compromise OpenAI
- 02Design security controls - focusing on measures with long lead times that benefit from advanced preparation
- 03Stress-test defenses with AI agent evaluations and penetration tests
Требования
- 01Are deeply technical across security and modern infrastructure, and are comfortable digging into the details of operating systems, cloud, containers, CI/CD, or distributed systems
- 02Have strong software engineering skills and enjoy building prototypes yourself
- 03Are interested in engaging with stakeholders and can do so effectively
- 04Bonus: have experience securing cloud infrastructure, and are deeply familiar with core components of the AI stack
Условия
- 01Compensation Range: $293K - $405K USD