Research Engineer, Privacy

In this role, you will design and prototype privacy-preserving machine-learning algorithms (differential privacy, secure aggregation, and federated learning) for large-scale deployment. You will measure and strengthen model robustness against privacy attacks such as membership inference, model inversion, and data memorization leaks, balancing utility with formal guarantees. You will develop internal libraries, evaluation suites, and documentation to make cutting-edge privacy techniques accessible to engineering and research teams. You will lead deep-dive investigations into the privacy–performance trade-offs of large models and publish insights to inform model-training and product-safety decisions. You will define and codify privacy standards, threat models, and audit procedures guiding the ML lifecycle, from data curation to post-deployment monitoring. You will collaborate with Security, Policy, Product, and Legal to translate evolving regulatory requirements into practical safeguards and tooling.