OpenAI3 дня назад

Исследователь, безопасность агентов, надзор и системные меры

Зарплата не указана
РЫНОК
26 250медиана по профессии
AI Researcher · 34 вакансий с указанной зарплатой
5 600половина предложений: 16 690–59 425143 300
Работодатель не указал зарплату — сравните с рынком сами.
Полная занятостьSan Francisco

Обязанности

  • 01Design, build, and evaluate system-level controls for agent actions like agent-based review
  • 02Plan how controls fit in a broader system including sandboxing with process isolation and permission boundaries
  • 03Work closely with a Codex harness engineering team to productionize the AI controls
  • 04Red-team end-to-end agentic systems to measure whether controls prevent data exfiltration, unsafe tool use, and other harmful outcomes
  • 05Improve the safety–productivity tradeoff by measuring and reducing missed harmful actions, unnecessary blocks, approval burden, and latency

Требования

  • 01Have strong systems or security instincts and can reason concretely about isolation boundaries, permissions, attack surfaces, and failure modes in complex systems
  • 02Enjoy turning ambiguous safety questions into concrete threat models, reproducible experiments, and practical mitigations
  • 03Can build robust experimental infrastructure and design evaluations that distinguish promising mitigations from brittle ones
  • 04Are deeply interested in frontier AI alignment, safety and control

Условия

  • 01Role is based in San Francisco, CA
  • 02Hybrid work model of 3 days in the office per week
  • 03Relocation assistance to new employees