- Explore the data landscape: profile on-chain, off-chain, fiat and KYC datasets to understand structures, gaps and lineage. Document findings for downstream engineering teams.
- Prototype features for ML & rules: translate typologies and investigator hypotheses into measurable candidate variables (e.g., velocity, counterparty risk scores, graph metrics) using SQL/Python and big data.
- Validate data quality & drift: run one-off QC checks, anomaly detection and basic stratified sampling to confirm a feature’s stability before production hand-off.
- Collaborate with modelers & investigators: iterate quickly on feature definitions, and refine logic based on model performance and investigative feedback.
- Maintain a living feature catalogue: version each prototype, capture business meaning, lineage and sample metrics so production data engineers can industrialize it.
- Support regulatory look-backs & ad-hoc research: replay historical data, craft quick queries and surface insights that help Compliance and Compliance Product teams respond to audits or enforcement actions.
- Stay current: monitor emerging AML data-science techniques (graph ML, LLM embeddings, anomaly detection) and assess their applicability to crypto and fiat monitoring.
- 4+ years in data engineering / analytics with hands-on feature-engineering and exploratory data analysis; AML or broader compliance experience is a plus.
- Expertise in SQL and Python (Pandas, PySpark, or similar) within notebook workflows, plus hands-on experience with big data stacks such as Spark/Hadoop, Databricks and Alibaba DataWorks
- Solid grounding in machine-learning fundamentals (supervised, unsupervised, evaluation metrics) and how features impact model performance.
- Experience translating AML / regulatory concepts into quantitative features—e.g., structuring, layering, sanctions exposure.
- Strong exploratory mindset: you’re comfortable with messy, ambiguous data and love turning it into structured insight.
- Effective communicator who can collaborate with downstream data engineers and data scientists and explain feature logic to investigators and auditors.
- Ability to work collaboratively in a fast-paced, dynamic environment.
- Self-directed, curious, and hungry to experiment with new data sources — blockchain analytics, vendor feeds, public datasets.
- Bonus: Working knowledge of the crypto ecosystem, VASP regulations, and typical AML data flows (KYT, KYC, TM, case management).
- Competitive total compensation package
- L&D programs and Education subsidy for employees' growth and development
- Various team building programs and company events
- Wellness and meal allowances
- Comprehensive healthcare schemes for employees and dependants
- More that we love to tell you along the process!
#LI-WWW
#LI-ONSITE
Top Skills
What We Do
Founded in 2017, OKX is one of the world’s leading cryptocurrency spot and derivatives exchanges. OKX innovatively adopted blockchain technology to reshape the financial ecosystem by offering some of the most diverse and sophisticated products, solutions, and trading tools on the market. Trusted by more than 20 million users in over 180 regions globally, OKX strives to provide an engaging platform that empowers every individual to explore the world of crypto.
In addition to its world-class DeFi exchange, OKX serves its users with OKX Insights, a research arm that is at the cutting edge of the latest trends in the cryptocurrency industry. With its extensive range of crypto products and services, and unwavering commitment to innovation, OKX’s vision is a world of financial access backed by blockchain and the power of decentralized finance.








