Researcher, Safety & Privacy (AI)

TL;DR

Researcher, Safety & Privacy (AI): Designing and building the next generation of privacy-preserving safety systems for frontier AI models with an accent on auditable, privacy-first mechanisms for harm detection. Focus on developing privacy-preserving monitoring, algorithmic auditing, and secure enclaves to mitigate frontier risks without exposing sensitive user data.

Location: San Francisco, USA

Salary: $295K – $445K + Equity

Company

OpenAI is an AI research and deployment company dedicated to ensuring that general-purpose artificial intelligence benefits all of humanity.

What you will do

• Design and implement privacy-first architectures for detecting and mitigating harmful model behaviors.
• Build frameworks for auditable private identification of high-risk content such as jailbreaks, cyber threats, or weaponization instructions.
• Develop strict, auditable mechanisms triggered specifically by harm signals.
• Drive the development of automated safety systems that preserve privacy at every level of the stack.

Requirements

• PhD or equivalent experience in Computer Science, Cryptography, Security, Machine Learning, or related fields.
• Proficiency in privacy-preserving computation, including secure enclaves, MPC, or differential privacy.
• Expertise in security, adversarial systems, and designing robust systems under adversarial threat models.
• Experience with AI safety, jailbreak detection, or model alignment.
• Ability to translate ambiguous problem spaces into formal frameworks and deployable systems.

Culture & Benefits

• Opportunity to work on the frontier of AI safety and privacy.
• Equity compensation provided alongside base salary.
• Inclusive work environment emphasizing diverse perspectives and equal opportunity.
• Focus on solving immense global challenges through the safe deployment of AI.