Machine Learning Engineer — Risk & AI
About The Position
The Machine Learning Engineer will build models and AI tools to detect fraud and protect users at a global cryptocurrency exchange. The role spans the full machine learning lifecycle, including problem formulation, feature engineering, model development, real-time deployment, monitoring, experimentation, and continuous improvement. It involves analyzing signals from areas such as on-chain activity, fiat transactions, trading behavior, account access, device intelligence, identity information, and customer interactions. The engineer will work with a multidisciplinary risk team and partner with engineering, product, and risk teams to deliver solutions that prevent losses while improving approval rates, reducing false positives, and supporting a reliable customer experience. The role also contributes to the risk organization's use of AI, including AI-assisted investigations, intelligent agents, and AI coding tools, with attention to validating outputs and establishing safe, scalable production practices.
Requirements
- A strong foundation in machine learning, with hands-on experience in deep learning and tree-based models such as XGBoost or LightGBM.
- Strong Python skills and experience training, evaluating, and deploying models.
- Practical experience building AI agents or LLM applications, including tool calling, retrieval, or workflow automation; prototypes and personal projects are welcome.
- Regular use of AI coding tools, with the ability to understand, test, and improve generated code.
- Familiarity with databases and data pipelines for preparing training data and supporting machine learning workflows.
- Good problem-solving, communication, and collaboration skills.
Nice To Haves
- Experience in account takeover (ATO), scam detection, or other fraud and risk use cases.
- Experience with LLM training, fine-tuning, evaluation, and alignment.
- Experience with reinforcement learning algorithms and their practical implementation.
- Experience with real-time machine learning systems, imbalanced datasets, or model explainability.
- Prior fraud or risk experience.
- Fluency in Mandarin.
Responsibilities
- Build, evaluate, and deploy machine learning models for fraud and risk detection.
- Improve data quality, features, and model performance while balancing fraud detection with customer experience.
- Develop AI agents to support investigations, summarize cases, retrieve evidence, and automate routine workflows.
- Use AI coding tools to accelerate development, testing, and debugging, while reviewing and validating their output.
- Work with engineering, product, and risk teams to deploy solutions and monitor their impact.
Benefits
- Competitive total compensation package.
- Learning and development programs for employee growth and development.
- Team-building programs and company events.
- Wellness and meal allowances.
- Comprehensive healthcare schemes for employees and dependants.
- A performance bonus and long-term incentives may be provided as part of the compensation package.
Stand Out From the Crowd
Upload your resume and get instant feedback on how well it matches this job.
What This Job Offers
Job Type
Full-time
Education Level
No Education Listed
