Machine Learning Engineer (Deepfake & Injection Attack Detection / Face Liveness)

As a Machine Learning Engineer in the Fraud & AI Integrity group, you will focus on deepfake detection, digital manipulation, and injection attack detection for selfie‑based identity verification.

What You Will Do (Core Responsibilities)

• Design, train, and deploy machine learning models for image‑based fraud detection, including deepfake detection, injection attack detection, and digital manipulation analysis in biometric verification.
• Work end‑to‑end across the ML lifecycle: dataset curation (large‑scale, noisy, adversarial datasets), model development and training, evaluation and iteration using fraud‑relevant metrics, production deployment and monitoring.
• Build robust data pipelines, including data validation, cleaning, labeling strategies, handling class imbalance, bias, and distribution shift.
• Define and execute evaluation frameworks focused on real‑world performance: precision/recall trade‑offs, false positive vs. fraud ...