Novel Abuse Red Teamer
OpenAI · San Francisco · Seattle · US - Remote
Frontier labremote$158k–$320k
At a glance
Highlights
- Lead pre- and post-deployment red teaming to harden AI models and products.
- Uncover novel abuse vectors by simulating real-world adversarial threats.
- Bridge security, product, and policy to strengthen detection mechanisms.
What they offer
- Equity
- Relocation assistance
Ideal candidate
Self-starting security thinker with an attacker mindset who loves finding novel abuse in live AI systems. You thrive cross-functionally and care deeply about securing AI through continuous learning.
Requirements
- Experience in application security, penetration testing, or red team operations
- Strong background in web application security and adversarial testing
- Hands-on experience testing web applications, AI systems and unique attack surfaces
- Proficiency with tools such as Burp Suite and Metasploit
- Attacker mindset with ability to translate findings into actionable insights
- Proven success working cross-functionally in fast-paced, dynamic environments
- remote policy
- 3 days in office per week
Lab profile
About OpenAI
Builds safe frontier AI models and products like ChatGPT for broad benefit.
What they build
- ChatGPT
- OpenAI API
- Frontier AI models
Known for
- Frontier-scale distributed ML training
- Massive GPU fleet and data center operations
- Exabyte-scale data lakes and streaming
- AI alignment and safety research
Key facts
- Operates one of the world's largest GPU fleets
Posted · Last seen