Researcher, Cyber Safety Training

OpenAI

San Francisco, CA • 1h ago • On-site

Mid

On-site

380,000 - 500,000 USD/yr

  1. Select offer
  2. Add resume
  3. Analyze
  4. Improve
  5. Apply
  6. Auto-send · soon

Match your resume with similar open roles

Upload your resume to automatically match with active openings similar to this role.

PDF up to 10 MB

Your resume is private & secure

Or go to the original job offer

Potential salary for Researcher, Cyber Safety Training role

Improve your resume now

$380,000 – $500,000/year

Quick Facts

  • Role: Researcher focused on cyber safety training for frontier AI models
  • Core focus: Train models to help with legitimate security work while refusing assistance that could enable harm

Description

You will work on large training runs that shape frontier models, studying both safe and unsafe assistance behaviors and using that learning to improve the next training run. The role involves designing complex, realistic cyber safety evaluations and researching post-training techniques that robustly improve cyber safety. You will collaborate with cross-functional teams to ensure safety improvements hold at scale.

Responsibilities

  • Collaborate with cybersecurity researchers to identify situations where context changes what help a model should provide
  • Design complex and realistic cyber safety evaluations
  • Research post-training techniques to improve cyber safety of frontier models
  • Integrate promising methods into large model runs and verify improvements at scale
  • Coordinate with cross-functional teams (research and policy/legal/other stakeholders) to meet high safety standards

Requirements

  • Hands-on machine learning experience
  • Trained or fine-tuned models and can explain an experiment that led to changes in training
  • Bring practical security judgment from industry, research, security team collaboration, or capture-the-flag experience
  • Ability to build and debug training-experiment code from data preparation through result checks
  • Enjoy working through ambiguous cases with domain experts and translating findings into concrete decisions for model responses

Benefits

  • Opportunity to work directly on frontier model training runs and post-training safety methods

See similar jobs

Explore similar jobs and use your resume score to choose where to apply next

See more

Unlock Full Resume Report