Researcher, Agent Safety, Oversight and System Mitigations

OpenAI
San Francisco, California, United States
Full Time
Hybrid
Senior
USD 380,000 – 500,000
Technology Information Technology Telecommunications

Posted 1 day ago

Apply to this job and hundreds more automatically

Get Started
Excellent 4.7

Job summary

This role focuses on oversight and system-level mitigations for AI agents to operate safely and autonomously, including designing controls, working with engineering teams, and evaluating safety measures to prevent harmful outcomes.

Responsibilities

Design, build, and evaluate system-level controls to ensure AI agents operate safely and autonomously. Work closely with engineering teams to productionize AI controls and red-team agentic systems to prevent harmful outcomes.

Qualifications

AI Safety Experiment Design Machine Learning Mitigation Strategies Operational Security Safety Protocols Security Security Boundaries System Controls Threat Modeling

Requires strong systems or security instincts with the ability to reason about isolation boundaries and failure modes. Candidates should be capable of turning ambiguous safety questions into concrete threat models and reproducible experiments.

English

Benefits

  • Medical insurance
  • Dental insurance
  • Vision insurance
  • Health savings accounts
  • Health fsa
  • Dependent care fsa
  • Commuter expenses
  • 401(k) retirement plan
  • Paid parental leave
  • Paid medical leave
  • Paid caregiver leave
  • Flexible pto
  • Paid company holidays
  • Paid sick time
  • Mental health support
  • Life insurance
  • Disability coverage
  • Learning and development stipend
  • Daily meals
  • Relocation support
  • Charitable donation matching
  • Wellness stipends

Company

OpenAI

OpenAI

Research Services
Location
San Francisco, California, United States
Website
openai.com

Apply to this job and hundreds more automatically

Get Started
Excellent 4.7
Pete DeQuarto avatar
Pete DeQuarto

AIApply is a total game-changer. Thanks to Auto-Apply, I have been applying to jobs I would never even have come across otherwise!

Akarshak Tanwar avatar
Akarshak Tanwar

In one week I applied to over 150 jobs and locked in 2 confirmed interviews, with a support team that was quick to respond. The auto-apply feature is fascinating and a real pleasure to use!

JC
Julian Carlin

It really worked. In under 48 hours it had applied to 100 jobs on my behalf without any time or effort from me. I am looking forward to seeing how it keeps improving.