Machine Learning Engineer (Compliance) - Global Payment - Singapore - Global Payment

The Global Payment Tech team is the core engine powering ByteDance's global payment and financial services, spanning payment acquiring, wallets, financial products, insurance, and foreign exchange for users and merchants worldwide.

We span engineering, data, and AI, building high-concurrency, highly available systems across multi-currency, multi-market complexity, and embedding AI into risk control, credit decisioning, and operations automation.

You will grow cross-disciplinary expertise at the intersection of payments, finance, and AI.

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 including TikTok.

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 (e.g. TikTok Live, TikTok Shop).

Responsibilities

• Develop a deep understanding of business models, payment flows, customer behavior, and regulatory requirements; translate emerging financial-crime risks into measurable signals, red flags, and AI-driven controls.
• Build AI-native AML capabilities using LLMs, multimodal models, graph learning, and machine learning to detect suspicious transactions, accounts, and behavioral patterns.
• Develop intelligent investigation solutions—including AI agents, retrieval-augmented generation (RAG), and automated case summarization—to improve alert triage, evidence collection, and investigator productivity.
• Design, train, evaluate, and deploy production-grade models with a strong focus on precision, recall, explainability, robustness, latency, and operational cost.
• Discover coordinated networks, money-laundering rings, and anomalous communities from large-scale transaction and entity graphs using graph algorithms and graph neural networks.
• Establish continuous learning and evaluation loops by incorporating investigator feedback, emerging typologies, regulatory changes, and model-monitoring results.
• Continuously optimize compliance strategies and model systems in a standardized, systematic, timely, and proactive manner.

Explore advances in AI and financial-crime prevention, rapidly validate promising approaches, and translate research into measurable business and compliance impact.

• Partner with compliance, investigation, product, engineering, and legal teams to ensure AI solutions are explainable, auditable, privacy-preserving, and compliant with applicable regulations.

Minimum Qualifications

• Bachelor’s degree or above in Computer Science, Computer Engineering, Statistics, Applied Mathematics, Data Science, or a related discipline.
• Strong foundation in data structures, algorithms, machine learning, and statistical modeling.
• Proficiency in at least one programming language, such as Python, Java, C++, or Go.
• Hands-on experience with at least one machine learning framework, such as PyTorch or TensorFlow, including model training, evaluation, deployment, and monitoring.
• Ability to work with large-scale, noisy, and highly imbalanced datasets and convert ambiguous risk problems into practical modeling solutions.
• Strong analytical thinking, ownership, and cross-functional communication skills.;

Preferred Qualifications

• Three or more years of experience in machine learning, risk control, fraud prevention, AML, trust and safety, or a related field.
• Experience building production applications with LLMs or multimodal models, including RAG, tool use, AI agents, fine-tuning, prompt engineering, and systematic evaluation.
• Experience with graph analytics, graph neural networks, anomaly detection, representation learning, or community detection.
• Familiarity with distributed data-processing and model-serving technologies, such as Spark, Flink, Ray, or Kubernetes.
• Experience designing human-in-the-loop systems and using expert feedback to continuously improve models and investigation workflows.
• Understanding of model explainability, AI safety, privacy protection, model governance, and regulatory audit requirements.
• Publications at leading conferences, meaningful open-source contributions, patents, or strong performance in relevant competitions are a plus.