| Job Position | Company | Posted | Location | Salary | Tags |
|---|---|---|---|---|---|
Binance | South East Asia |
| |||
Copperco | Remote | $90k - $164k | |||
Bitgo | Remote | $180k - $240k | |||
Binance | Brisbane, Australia |
| |||
| Learn job-ready web3 skills on your schedule with 1-on-1 support & get a job, or your money back. | | by Metana Bootcamp Info | |||
Lobster | Paris, France | $40k - $80k | |||
SafeGlobal | New York, NY, United States | $87k - $112k | |||
Binance | South East Asia |
| |||
Ethereum Foundation | Remote |
| |||
Blockaid | Tel Aviv, Israel | $88k - $100k | |||
Stellar | Remote | $160k - $205k | |||
Okx | Remote | $240k - $360k | |||
Mysten Labs | United States | $150k - $225k | |||
MoonPay | Krakow, Poland | $122k - $123k | |||
Bitso | Latin America | $98k - $103k | |||
Bitso | Latin America | $86k - $102k |
Data Scientist, Risk (Machine Learning & Fraud Detection)
Responsibilities
- 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.
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.
What does a data scientist in web3 do?
A data scientist in web3 is a type of data scientist who focuses on working with data related to the development of web-based technologies and applications that are part of the larger web3 ecosystem
This can include working with data from decentralized applications (DApps), blockchain networks, and other types of distributed and decentralized systems
In general, a data scientist in web3 is responsible for using data analysis and machine learning techniques to help organizations and individuals understand, interpret, and make decisions based on the data generated by these systems
Some specific tasks that a data scientist in web3 might be involved in include developing predictive models, conducting research, and creating data visualizations.