Research Engineer, Privacy

The role

You will design and prototype privacy-preserving machine-learning algorithms and measure model robustness against privacy attacks. You will develop internal libraries and collaborate across teams to translate regulatory requirements into technical safeguards.

What you will do

• Design and prototype privacy-preserving machine-learning algorithms that can be deployed at OpenAI scale.
• Measure and strengthen model robustness against privacy attacks.
• Develop internal libraries, evaluation suites, and documentation.
• Lead deep-dive investigations into the privacy–performance trade-offs of large models.
• Define and codify privacy standards, threat models, and audit procedures.
• Collaborate across Security, Policy, Product, and Legal to translate regulatory requirements into technical safeguards.

Required qualifications

• Hands-on research or production experience with PETs.
• Fluent in modern deep-learning stacks (PyTorch/JAX).
• Comfortable turning cutting-edge papers into reliable, well-tested code.
• Track record of publishing (or implementing) novel privacy or security work.

Nice to have

• Curious about using AI tools and agents to improve research and evaluation workflows.

Benefits

• Relocation assistance is available.

Before you apply

• Background checks for applicants will be administered in accordance with applicable law.

About the company

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