Über
The Cadmus Group provides technology-empowered advisory and implementation services to various organizations. The Data Scientist will design, build, and implement analytical models to combat financial crimes, requiring a blend of quantitative expertise and data science skills in the banking or financial services sectors.
Responsibilities : • Develop and implement rule-based and scenario-driven detection models using Python and PySpark to identify suspicious transaction patterns and potential financial crimes. • Design and build scalable data processing pipelines using PySpark on distributed environments, enabling efficient processing of high-volume transactional data. • Utilize AWS cloud services such as Amazon S3, AWS Glue, and Amazon EMR to store, transform, and process large datasets for model development and automated monitoring workflows. • Write optimized SQL queries to extract, transform, and validate structured and semi-structured financial data from enterprise data warehouses and data lakes. • Collaborate with business stakeholders, compliance teams, and risk analysts to gather functional requirements and translate them into technical solutions, including new monitoring rules and detection scenarios. • Develop automated testing frameworks in Python and PySpark to validate rule logic, scenario accuracy, and data quality before deployment to production environments. • Implement data validation, anomaly detection, and rule-testing pipelines to ensure accuracy and regulatory compliance in transaction monitoring systems. • Work with AWS-based data lakes and lakehouse architectures to integrate transactional data, reference datasets, and external risk indicators for enhanced analytics. • Perform data transformation and feature engineering using PySpark and SQL to prepare datasets for risk modeling and rule evaluation. • Maintain detailed technical documentation, code repositories, and testing artifacts following industry best practices and internal governance standards. • Support CI/CD deployment processes and version control (Git) for rule development and data pipeline updates. • Monitor and optimize data pipeline performance, Spark jobs, and SQL queries to ensure efficient processing and scalability in cloud environments. • Work closely with bank personnel and cross-functional teams to support day-to-day AML monitoring operations, scenario tuning, and regulatory compliance initiatives.
Qualifications : Required : • Master’s Degree in Information Science/ Data Science/ Applied Economics/ Applied Statistics and 3 - 5 years of relevant experience. • Solid, proven technical foundation in SQL and Python and databases. • Proven understanding of machine learning concepts and hands-on capability to build ML projects and analytical tools. • Strong attention to detail, specifically regarding the nuances of financial products, external/internal entities, and the strict assumptions inherent in transaction monitoring. • Ability to independently approach complex, real-world data problems and execute daily responsibilities with minimal supervision. • Comfortable running or participating in daily Agile/Scrum meetings to present iterative progress, gather feedback, and document subsequent action items.
Company :
Cadmus is a non-profit, and corporate clients address challenges concerning energy and the environment. Founded in 1983, the company is headquartered in Watertown, USA, with a team of 1001-5000 employees. The company is currently Late Stage.
Sprachkenntnisse
- English
Hinweis für Nutzer
Dieses Stellenangebot stammt von einer Partnerplattform von TieTalent. Klicken Sie auf „Jetzt Bewerben“, um Ihre Bewerbung direkt auf deren Website einzureichen.