Research Engineer, Privacy

OpenAI; United States; Remote; USD 180,000 - 240,000; Full time

Job summary

OpenAI is seeking a Privacy Engineer in San Francisco to advance privacy-preserving machine learning techniques across our AI systems. The role focuses on differential privacy, federated learning, and data anonymization while balancing data utility with strong privacy guarantees.

You will design scalable privacy methods, develop evaluation tools, and publish insights to guide model training and production deployment. Relocation assistance is available.

Qualifications

• Experience designing privacy-preserving ML algorithms for large-scale systems.
• Strong understanding of differential privacy and related techniques.
• Familiarity with federated learning and data anonymization methods.
• Knowledge of attacks such as membership inference and model inversion.

Responsibilities

• Design privacy-preserving ML algorithms deployable at OpenAI scale.
• Measure robustness against privacy attacks while balancing utility and guarantees.
• Develop internal libraries and evaluation tools for privacy features.
• Lead investigations into privacy–performance trade-offs for large models.

Skills

Privacy-aware ML

Differential privacy

Federated learning

Data anonymization

Privacy attacks knowledge

Tools

Secure aggregation framework

Evaluation suites

Job description

About the Team

The Privacy Engineering Team at OpenAI is committed to integrating privacy as a foundational element in OpenAI's mission of advancing Artificial General Intelligence (AGI). Our focus is on all OpenAI products and systems handling user data, striving to uphold the highest standards of data privacy and security. We build essential production services, develop novel privacy-preserving techniques, and equip cross-functional engineering and research partners with the necessary tools to ensure responsible data use. Our approach to prioritizing responsible data use is integral to OpenAI's mission of safely introducing AGI that offers widespread benefits.

About the Role

As a part of the Privacy Engineering Team, you will work on the frontlines of safeguarding user data while ensuring the usability and efficiency of our AI systems. You will help us understand and implement the latest research in privacy-enhancing technologies such as differential privacy, federated learning, and data memorization. Moreover, you will focus on investigating the interaction between privacy and machine learning, developing innovative techniques to improve data anonymization, and preventing model inversion and membership inference attacks. This position is located in San Francisco. Relocation assistance is available. In this role, you will:

• Design and prototype privacy-preserving machine-learning algorithms (e.g., differential privacy, secure aggregation, federated learning) that can be deployed at OpenAI scale.
• Measure and strengthen model robustness against privacy attacks such as membership inference, model inversion, and data memorization leaks—balancing utility with provable guarantees.
• Develop internal libraries, evaluation suites, and documentation that make cutting-edge privacy techniques accessible to engineering and research teams.
• Lead deep-dive investigations into the privacy–performance trade-offs of large models, publishing insights that inform model‑training and prod