Research Engineer — Privacy

منذ 4 أيام

Ras alKhaimah, Ras Al Khaimah, الإمارات العربية المتحدة Meramia Technologies دوام كامل

The seat sits between the models we train and serve and the data those models must not memorise — deep learning research, systems work, and the privacy techniques that have to hold when the estate is a client's.Prototype and land privacy-enhancing algorithms — differential privacy, secure aggregation, federated learning — on the training and inference stacks we actually run.

Red-team the models for membership inference, inversion, and training-data memorisation. Write the failure down before someone else finds it. Build the evaluation suites and diagnostic libraries ML engineers can use across a model's life, not a one-off notebook.

Sit with research, platform, security, legal and product so a regulation or a security principle becomes a guardrail in code.

Investigate the privacy–utility trade: capability, latency and cost against a guarantee you can state.

What you will doPrototype and land privacy-enhancing algorithms — differential privacy, secure aggregation, federated learning — on the training and inference stacks we actually run.

Red-team the models for membership inference, inversion, and training-data memorisation. Write the failure down before someone else finds it. Build the evaluation suites and diagnostic libraries ML engineers can use across a model's life, not a one-off notebook.

Sit with research, platform, security, legal and product so a regulation or a security principle becomes a guardrail in code.

Investigate the privacy–utility trade: capability, latency and cost against a guarantee you can state.

What you bringPyTorch or JAX, and research-grade Python you will test rather than demo.

Differential privacy (including DP-SGD), secure multiparty computation, or federated learning — implemented, not only cited.

The attack surface: extraction, membership inference, poisoning — and how you measured it. A paper you can turn into a well-tested module without losing the claim that made the paper worth reading.

The ability to explain a mathematical privacy guarantee to an engineer and to a policy lead in the same week.

Useful, not requiredPeer-reviewed work or open-source in privacy, security, cryptography or machine learning — NeurIPS, ICLR, USENIX Security, IEEE S&P, or the equivalent venue. PETs on a distributed train or a high-throughput inference path, not only on a single node.

The first quarterAudit the privacy evaluations and training workflows already in use.

Ship one automated evaluation or differential-privacy module into the internal ML path.

Write the privacy–utility result for the architectures we serve, with a deployable recommendation.