Machine Learning Engineer (Payment & Risk) - Global Payment - Singapore

职位描述

The Global Payment team of ByteDance provides payment solutions - including payment acquisitions, disbursements, transaction monitoring, payment method management, foreign exchange conversion, accounting, reconciliations, and so on to ensure that our users have a smooth and secure payment experience on ByteDance platforms.

The Global Payments Compliance team's duty is to establish a comprehensive and strong compliance foundation with sanction screening, transaction monitoring, risk rating system to systematically enable business models, revenue growth, and protect executives from possible legal liabilities for ByteDance

Responsibilities:

- Refine payment risk feature engineering and fraud evaluation systems;

- Develop universal fraud and account takeover (ATO) detection models for global payment scenarios;

- Explore the application of sequence models, graph networks, and LLMs in risk control scenarios;

- Develop universal machine learning models to identify cross-border and regional payment risks from a global perspective;

- Optimize modeling workflows to improve development/deployment efficiency and reduce maintenance costs;

- Research and apply cutting-edge machine learning algorithms within the risk control domain.

任职要求

Minimum Qualification(s):

- Bachelor’s degree and above with majors in computer science, computer engineering, statistics, applied mathematics, data science or other related disciplines;

- Solid experience with data structures and algorithms;

- Familiar with at least one framework of TensorFlow / PyTorch / MXNet and its training and deployment details;

- Strong coding skills in at least one of the following programming languages, e.g. Python, Java, C/C++.

Preferred Qualification(s):

- Minimum 3 years of relevant experience;

- Experience in NLP, graph mining, or fraud detection;

- Experience in credit risk, payment risk, or search/recommendation systems;

- CCF A/B Papers or competition awards are preferred