Senior /Staff AI Engineer
Salary not listed • Hong Kong, Hong Kong SAR; Singapore, Singapore • Full-time
Posted 7mo ago
This job has been open for more than 60 days. It may no longer be actively hiring, so check with the company before putting a lot into an application.
About the job
OKX is seeking a Senior AI Engineer to design, build, and own key identity-risk and trust models. This role is crucial for detecting and preventing identity fraud, account takeover, and organized abuse in real-time for a global financial platform. You will be responsible for creating models that integrate various data sources, including identity verification, device and geo data, and user behavior, to generate trust and risk signals. This is an end-to-end role, from research to production, where you will ship models into high-risk, large-scale production environments and contribute to raising the team's technical standards.
Responsibilities
- Design and ship risk models that fuse face/liveness/document verification scores, device, IP, geo signals, and behavioral data for high-concurrency real-time decisioning.
- Build entity graphs and apply community detection, clustering, and GNN methods to detect fraud rings and large-scale abuse.
- Engineer real-time and offline behavioral features and build sequence models to detect account takeover, bot behavior, and abnormal sessions.
- Develop reliable identity-trust inputs for risk decisions using biometric features and document-forgery/DeepFake signals, potentially building models or collaborating with specialized teams.
- Deliver measurable results, manage ambiguity, and partner with backend, product, infrastructure, risk, and compliance teams to integrate models into the production decision chain.
- Own metric definitions, the balance between false positives and missed fraud, pass rate, monitoring, and drift handling.
- Experiment with graph learning, multimodal fusion, and AI agents, staying current with academic and industry advances to translate them into practical defenses.
- Contribute to design reviews, share applied-AI best practices, and mentor junior engineers.
Requirements
- 5+ years of hands-on experience building risk-control, fraud-detection, or identity-trust models.
- Significant experience deploying ML systems into production.
- Experience applying graph mining, community detection, clustering, or GNN methods to fraud or abuse detection.
- Solid experience with behavioral feature engineering and sequence modeling, including real-time feature pipelines.
- Strong proficiency with PyTorch and/or TensorFlow.
- Solid experience with production ML systems.
- Strong coding ability (e.g., Python, SQL).
- System-level thinking to design end-to-end solutions with high availability and low latency.
- Understanding of how fraudsters adapt and how to evaluate and iterate defenses against evolving attacks.
- Strong communication skills and experience working across engineering, product, and risk teams.
- Bachelor's degree or higher in Computer Science, Electrical Engineering, or a related field.