Privacy Engineering Researcher (DP/FL) & ML Safety

The Consensus; San Francisco (CA); On-site; USD 180,000 - 280,000; Full time

Benefits offered by this job

Relocation assistance

Job summary

OpenAI is seeking a Privacy Engineer in San Francisco to safeguard user data while enabling scalable AI. You will design privacy‑preserving ML methods, implement differential privacy, secure aggregation, and federated learning, and work with researchers to translate theory into production.

Relocation assistance is available. You will collaborate across teams to set standards and respond to evolving privacy regulations, helping OpenAI advance safe and responsible AI.

Qualifications

• Hands-on research or production experience with PETs.
• Fluent in modern deep‑learning stacks (PyTorch/JAX) and turning papers into tested code.
• Experience stress‑testing models for private data leakage and explaining attack vectors.
• Track record of publishing or implementing privacy or security work.
• Thrives in fast‑moving cross‑disciplinary environments balancing research and production.

Responsibilities

• Design and prototype privacy‑preserving ML algorithms deployable at OpenAI scale.
• Measure and strengthen model robustness against privacy attacks while balancing utility and guarantees.
• Develop internal libraries, evaluation suites, and documentation for privacy techniques.
• Lead investigations into privacy/performance trade‑offs of large models; publish insights.
• Define privacy standards, threat models, and audit procedures across the ML lifecycle.
• Collaborate with Security, Policy, Product, and Legal to translate regulatory requirements into safeguards.

Skills

PETs

PyTorch/JAX

Differential privacy

Security audits

Model inversion defense

Tools

Secure aggregation

Federated learning

Job description

OpenAI is seeking a Privacy Engineer in San Francisco to safeguard user data while enabling scalable AI. You will design privacy‑preserving ML methods, implement differential privacy, secure aggregation, and federated learning, and work with researchers to translate theory into production.

Relocation assistance is available. You will collaborate across teams to set standards and respond to evolving privacy regulations, helping OpenAI advance safe and responsible AI.