Binance is a leading global blockchain ecosystem behind the world’s largest cryptocurrency exchange by trading volume and registered users. We are trusted by over 250 million people in 100+ countries for our industry-leading security, user fund transparency, trading engine speed, deep liquidity, and an unmatched portfolio of digital-asset products. Binance offerings range from trading and finance to education, research, payments, institutional services, Web3 features, and more. We leverage the power of digital assets and blockchain to build an inclusive financial ecosystem to advance the freedom of money and improve financial access for people around the world.
We are seeking a highly skilled and motivated Data Scientist to join our Fraud Detection & Risk Intelligence team. In this role, you will focus on identifying on-chain and off-chain fraud groups, uncovering complex user relationships, and building scalable machine learning models and data pipelines. Your work will be critical in protecting our ecosystem and users from evolving fraud patterns.
You will work cross-functionally with risk engineers, data engineers, product managers, and operations teams to convert large-scale, complex data into actionable insights and real-time protections.

REQUIREMENTS

• Minimum of 3 years of hands-on experience in developing machine learning models and building ML engineering solutions that drive tangible business outcomes.
• Strong expertise in user behavior modeling, fraud detection, graph analytics, or working with graph neural networks (GNNs).
• Proficient in unsupervised learning methods, including clustering, anomaly detection, and representation learning.
• Solid experience with on-chain data analysis, such as decoding blockchain transactions and clustering wallets based on behavioral and transactional patterns.
• Advanced programming skills in Python (required); familiarity with Scala or Java is a plus.
• Proven experience working with large-scale data processing frameworks and infrastructure, including Spark, Hive, Kafka, and Flink.
• Demonstrated success in deploying machine learning models or decision systems into production environments.
• Holds a Master’s degree in Data Science, Machine Learning, Computer Science, or a related field, or possesses equivalent practical experience.
• Comfortable working with large datasets at the terabyte to petabyte scale.
• Thrives in fast-paced, ambiguous, and early-stage (0 1) problem spaces with high ownership and initiative.
• Deep interest in fraud prevention, cryptocurrency risk, and graph-based intelligence.
• Excellent written and verbal communication skills, with the ability to clearly convey complex technical concepts in English to be able to coordinate with overseas partners and stakeholders.

• Feature Engineering & Data Infrastructure: Design and maintain scalable data pipelines (PB-scale) using technologies such as Spark, Hive, Flink, Trino, and Kafka. Collaborate with data engineers to build reusable, production-ready features for ML models and real-time decision engines.
• Fraud Group & Sybil Detection: Develop graph-based models and algorithms to detect coordinated fraud behavior using device data, IP addresses, fund flows, and user behavior. Design unsupervised clustering and rule-based systems to identify Sybil attacks and fraudulent account rings.
• User Behavior & Pattern Mining: Analyse large-scale user activity to identify behavioral anomalies such as automation, rapid transactions, or coordinated arbitrage activity. Train machine learning models for anomaly detection and integrate outputs into automated risk controls.
• On-Chain Data Intelligence: Conduct deep analysis of blockchain transaction data to cluster wallets, decode transactions, and identify suspicious smart contract patterns. Apply on-chain behavior modeling to detect malicious activity across addresses and platforms.
• Projects You May Work On: Building anomaly detection systems to stop automated bots and cross-account funding behaviors. Developing scalable ETL pipelines for real-time fraud scoring engines. Implementing graph algorithms to uncover hidden fraud rings within transaction and identity networks. Researching and prototyping on-chain Sybil scoring models using wallet clustering and contract analysis.