Model Policy Manager, Agentic Safety

OpenAI

San Francisco, CA • 32m ago • Hybrid

Mid

Hybrid

207,000 - 335,000 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 Model Policy Manager, Agentic Safety role

Improve your resume now

$207,000 – $335,000/year

Quick Facts

  • Role: Model Policy Manager, Agentic Safety

  • Focus: Agentic safety, model misalignment risks, and long-horizon behavior

Description

In this role, you will shape how real-world risks from model misalignment are understood and addressed as models become more autonomous and operate over longer horizons. You will investigate how misaligned behavior emerges across extended trajectories and translate those insights into behavioral policies, evaluations, monitoring, and safeguards. Your work turns alignment and safety concerns into empirically grounded improvements to frontier AI systems.

Responsibilities

  • Identify vulnerabilities that emerge as models interact with tools, data, and external systems, and translate them into model- and system-level safeguards

  • Develop threat models and empirical frameworks for understanding harmful outcomes from misaligned behavior

  • Build frameworks for understanding harmful outcomes arising from model misalignment

  • Identify underlying behaviors and system conditions that drive harmful outcomes

  • Turn findings into policy frameworks, evaluation criteria, online measurement, and safeguards

  • Develop human data campaigns and gold sets to ground measurement and evaluation of emerging behaviors and risks

  • Partner with research, engineering, security, and product teams to shape model and system safety

  • Inform deployment decisions, system cards, safeguards reports, and the broader approach to agentic safety

  • Build monitoring approaches to detect regressions and emerging risks after deployment

Requirements

  • Strong background in AI agent safety, privacy, security, cybersecurity, or adjacent fields with an adversarial mindset

  • Demonstrated interest in AI alignment and understanding of technical drivers of misaligned model behavior

  • Technical fluency to work with evaluation and training data and interpret data insights and limitations

  • Comfort working hands-on with model data and evaluation results, including inspecting examples, analyzing failure patterns, assessing data quality, and distinguishing policy failures from grader, model, or system failures

  • Use empirical evidence to develop and refine safety policies and safeguards

  • Translate complex or ambiguous alignment risks into precise behavioral expectations and measurable evaluation criteria

  • Work effectively across research, engineering, security, product, and policy

  • Communicate clearly about complex and uncertain technical risks

  • Enjoy fast-paced, collaborative research environments where priorities shift as models, evidence, and risks change

Benefits

  • Hybrid schedule: three days in the office per week with optional work from home on Thursdays and Fridays

  • Relocation support for new employees

See similar jobs

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

See more

Unlock Full Resume Report