OpenAI
Researcher, Frontier Cybersecurity Risks
$380K–$500K
San Francisco · Full-time · Posted Aug 3, 2026
About the job
Designs and implements safeguards to reduce severe cybersecurity misuse across OpenAI products, testing and improving protections as models and threats evolve.
What you'll do
- Design and implement prevention, monitoring, detection, and enforcement components for cybersecurity misuse.
- Integrate safeguards across products and evaluate trade-offs involving coverage, latency, model utility, and user privacy.
- Collaborate on threat modeling and conduct testing and red-teaming against evolving cyber threats.
What they ask for
- Demonstrated experience in deep learning and transformer models.
- Proficiency with frameworks such as PyTorch or TensorFlow.
- Strong foundation in data structures, algorithms, and software engineering principles.
- Significant experience designing and deploying technical safeguards for abuse prevention, detection, and enforcement at scale.
Nice to have
- Background knowledge in cybersecurity or adjacent fields.
Pay
USD $380K – $500K base salary
Tools
PyTorch, TensorFlow
AI focus
Build and evaluate safeguards against AI-enabled cybersecurity misuse, including model-enabled attacks and evolving attacker behaviors.
Model-written summary · the original posting is authoritative