Model Policy Manager, Emerging AI Misuse

Added
1 hour ago
Type
Full time
Salary
Upgrade to Premium to se...

Related skills

ai threat modeling policy evaluation ai safety

πŸ“‹ Description

  • Build and update threat models as capabilities evolve.
  • Define when models should help, limit assistance, or refuse in situations where the same capability
  • Turn expert safety judgment into instructions, training examples, and evaluations that teach models
  • Turn threat models into evaluation scenarios and grading guidance.
  • Analyze model outputs, red-team findings, and deployment data to identify where models enable
  • Partner with research, engineering, security, and product teams to apply findings to model

🎯 Requirements

  • Hands-on experience building, testing, or assessing dual-use technologies, or a track record of
  • Deep practical experience in one relevant domain and the judgment to know when to bring in experts
  • Ability to assess whether a capability demonstrated in a test materially changes what someone could
  • Ability to translate technical evidence and uncertainty into clear policy boundaries and measurable
  • Experience analyzing gold sets, evaluation results, and training data to spot inconsistent human
  • Comfortable working hands-on with model data and evaluation results.

🎁 Benefits

  • Offers full-time position with hybrid work model (3 days per week in office, optional work from
  • Relocation support available

🚚 Relocation support

Get alerts for new remote engineering jobs
A weekly email with new matches. Unsubscribe anytime.
Share job

Meet JobCopilot: Your Personal AI Job Hunter

Automatically Apply to Engineering Jobs. Just set your preferences and Job Copilot will do the rest β€” finding, filtering, and applying while you focus on what matters.

Related Engineering Jobs

See more Engineering jobs β†’