Protection Scientist Engineer, Integrity
OpenAI · San Francisco
Frontier labremote$220k–$425k
At a glance
Highlights
- Design defenses against sextortion, trafficking, and nation-state misuse.
- Build detection systems that adapt as adversaries change tactics.
- Protect frontier AI products from jailbreaks and coordinated abuse.
What they offer
- Equity
Ideal candidate
Systems thinker who blends harm-domain expertise with investigation and data skills. Motivated to translate evolving abuse patterns into scaled protections and drive cross-functional defense.
Requirements
- Design, build, evaluate and maintain production harm detection systems
- Develop signals, classifiers and pipelines using SQL, Python, ML and LLMs
- Drive protection strategy and lead cross-functional execution for a harm area
- Participate in on-call rotation and handle sensitive content investigations
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