Researcher, Loss Of Control

OpenAI

San Francisco, United States
Deep learning and transformer models
Pytorch or tensorflow proficiency
Data structures, algorithms, software engineering
The Preparedness team is tasked with identifying, tracking, and preparing for catastrophic risks related to frontier AI models

Job Summary

  • The Preparedness team is tasked with identifying, tracking, and preparing for catastrophic risks related to frontier AI models.
  • As a Researcher for loss of control mitigations, you will help design and implement an end-to-end mitigation stack to reduce the risk of intentionally subversive or insufficiently controllable model behavior.
  • This role requires strong technical depth and close cross-functional collaboration to ensure safeguards are enforceable, scalable, and effective.

Matching Summary

The Preparedness team is tasked with identifying, tracking, and preparing for catastrophic risks related to frontier AI models.

Skills & Requirements

Must-have

  • Deep learning and transformer models
  • PyTorch or TensorFlow proficiency
  • Data structures, algorithms, software engineering
  • Mitigation components for loss of control
  • Cross-functional collaboration
  • Rigorous testing and red-teaming

Nice-to-have

  • Alignment, control, interpretability
  • Adversarial ML background
  • Passion for AI safety

Key Requirements

  • Demonstrated experience in deep learning
  • Proficiency with PyTorch or TensorFlow
  • Strong foundation in data structures
  • Familiarity with LLM training methods
  • Experience designing technical safeguards

Work Rights

Not specified

Tailored Resume

Cover Letter