At Deep Native, we build high-impact data and AI teams for ambitious companies. We're searching for a Data Scientist to join one of our fintech clients — tackling money laundering, fraud, and financial crime at scale through modern, cloud-native transaction monitoring.
If you like turning billions of transactions into defensible, real-world detection of suspicious activity, read on.
Toronto (Hybrid)
What you'll do Analyze large-scale transaction, customer, and account data to detect money-laundering and suspicious-activity patterns across multi-year lookback windows
Build, test, and tune detection logic for AML typologies — structuring, layering, rapid movement of funds, velocity anomalies
Engineer leakage-aware features with point-in-time joins, and build analysis-ready datasets on a bronze → silver → gold medallion architecture (Azure Databricks)
Translate legacy rules into transparent, testable spec-as-code
Own data quality and reconciliation — completeness checks, amount-drift across layers, evidence-ready outputs
Validate model performance, monitor for drift, and document methodology with full audit traceability
Build BI views and metrics — alert volumes, false-positive rates, conversion — for risk and leadership
What you bring Strong Python and SQL; hands-on PySpark and Spark SQL on Databricks




Feature engineering and model development on large-scale data — ideally fraud, AML, or financial risk
Solid statistics / ML and model validation, with a healthy respect for data leakage
Comfort in a regulated, audit-conscious environment with disciplined documentation
Clear communication of complex signals to non-technical partners
Nice to have AML / transaction-monitoring or fraud-analytics background
Delta Lake, Lakeflow/Jobs, MLflow exposure
FINTRAC / regulatory familiarity; ACAMS (CAMS) a plus
Power BI or similar for analytics reporting
Want to ramp up first? We keep an open, public-protected learning resource so you can get hands-on with exactly this kind of work — AML/TM modernization on Databricks, Spark SQL & PySpark labs, data-quality & reconciliation, point-in-time feature engineering, and role-based prep
Why this role High-ownership seat on a core financial-crime problem at a growing fintech
Modern stack — Azure Databricks, Spark, Delta — and the freedom to build
Backed by Deep Native — we stay in your corner through the process and beyond
Interested, or know someone perfect for this? DM me or comment below — referrals always welcome.
#DataScience #AML #TransactionMonitoring #Fintech #FraudPrevention #Databricks #PySpark #MachineLearning #Hiring #Toronto #DeepNative

#J-18808-Ljbffr

📌 Data Scientist — AML / Transaction-Monitoring Analytics (Fintech) (Ontario)
🏢 Socket.dev
📍 Ontario