Data Scientist II, Anti Money Laundering Transaction Monitoring

BMO•Chicago, IL

1d•$69,000 - $127,800

About The Position

Data Scientist, AML Transaction Monitoring & Machine Learning Uses advanced analytics, machine learning, and statistical techniques to design, develop, and optimize Anti-Money Laundering (AML) transaction monitoring solutions. Leverages large-scale transactional, customer, and investigative datasets to identify suspicious activity, improve detection effectiveness, and reduce false positives. Partners with Financial Intelligence Unit (FIU), AML Compliance, Model Risk Management, Data Management, and Technology teams to deliver data-driven solutions that enhance the Bank's financial crime detection capabilities while meeting regulatory and governance requirements. The successful candidate will contribute throughout the model lifecycle, including data acquisition, feature engineering, model development, validation support, implementation, ongoing monitoring, and model optimization. The role requires translating complex analytical findings into practical business insights and recommendations that strengthen the AML program and support risk-based decision making.

Requirements

Typically between 4 - 6 years of relevant experience and post-secondary degree in a related field of study or an equivalent combination of education and experience.
Experience with Python and SQL for large-scale data analysis, feature engineering, and model development.
Strong understanding of statistical analysis, machine learning algorithms, and model performance measurement.
Experience working with large structured and semi-structured datasets.
Experience using version control tools and code repositories (e.g., Git, GitHub, Azure DevOps) to support collaborative development and reproducible analytical workflows.
Familiarity with generative AI tools and AI-assisted development practices (e.g., Microsoft 365 Copilot, GitHub Copilot, LLM-based coding assistants) to improve productivity, documentation, and analytical workflows.
Ability to communicate technical concepts effectively to both technical and non-technical audiences.

Nice To Haves

Experience in AML, transaction monitoring, fraud analytics, sanctions screening, financial crime compliance, or risk analytics.
Knowledge of AML regulations, suspicious activity reporting processes, financial crime typologies, and transaction monitoring methodologies.
Experience developing, tuning, validating, or monitoring machine learning and analytical models used for risk detection or decision support.
Experience with anomaly detection, clustering, graph analytics, network analysis, or other advanced analytical techniques.
Familiarity with model governance, model validation, regulatory examinations, audit activities, and model documentation requirements.
Experience working with customer, transaction, payment, alert, case, and investigative datasets.
Experience using Dataiku, Databricks, SAS, Spark, Hadoop, cloud-based analytics platforms, or similar technologies.
Demonstrated ability to leverage AI tools to improve analytical efficiency, automate repetitive tasks, accelerate code development, and enhance documentation quality.
Advanced degree in Statistics, Mathematics, Data Science, Computer Science, Economics, Engineering, or a related quantitative discipline.

Responsibilities

Design, develop, test, and deploy machine learning and analytical models used for AML transaction monitoring and suspicious activity detection.
Analyze large volumes of customer, transactional, payment, and alert data to identify emerging money laundering risks, typologies, and anomalous behavior patterns.
Develop and evaluate supervised and unsupervised machine learning approaches to improve detection effectiveness and investigator outcomes.
Conduct feature engineering and exploratory data analysis to identify behavioral indicators associated with financial crime risk.
Perform quantitative assessments of model performance, including detection effectiveness, productivity, false positive reduction, and risk coverage.
Support model tuning, optimization, and revalidation activities to ensure models continue to perform as intended.
Assess data quality and data lineage and partner with data management teams to resolve issues affecting model performance and reliability.
Prepare clear and comprehensive model development, testing, and governance documentation to support model validation, audit, and regulatory reviews.
Translate analytical findings into actionable recommendations for AML Compliance, FIU, and senior management.
Collaborate with business stakeholders, investigators, model governance, and technology partners to prioritize enhancements and implement solutions.
Research emerging financial crime typologies, machine learning techniques, and industry best practices to continuously improve monitoring capabilities.
Contribute to strategic initiatives involving AI, machine learning, graph analytics, network analysis, and other advanced analytical approaches applicable to financial crime detection.
Ensure all analysis and model development activities comply with applicable regulatory requirements, internal policies, and model risk management standards.
Take measured risks while protecting the bank by applying the Risk Management Framework and exercising sound risk-based judgment.