Senior AML Data Scientist State Street
Quincy, MA

Job Description

.The successful candidate will execute on initiatives related to next generation financial crime and other specialized risk models which include transaction monitoring, peer grouping, customer risk rating, name screening, decision reapplication, and other predictive financial analytics. The individual will engineer features, investigate patterns, and implement other more advanced modeling methods to continually enhance our AML methodologies. They will assist in developing modeling and data mining skills in other Predictive Analytics personnel, be responsible for peer reviewing other's work, and lead project teams as needed.

The position reports to the Director of AML Analytics and will require direct or indirect leadership of high-profile research projects from design through conclusions and recommendations, as well as participation in the implementation plan as subject matter expert. The position will also lead training and development of Data Science staff on advanced statistical and data modeling techniques. The position requires the use and understanding of advanced statistical techniques, as well as the ability to partner with business segments to identify opportunities and communicate progress and findings.

The successful candidate must be highly analytical and possess a strong passion for data science and accountability, setting high standards, and providing high-quality results. The Sr. Data Scientist will have demonstrated experience as a problem-solver, working alongside AML management and business partners, and act as a trusted advisor.

Responsibilities Include:

* Lead development, implementation and continuous improvement of financial crime models and analytic strategies;
* Develop effective machine learning systems for segmentation, classification, estimation, matching, optimization, natural language, validation, testing, etc.
* Structure business problems and drive viable, data-driven hypotheses in collaboration with business and product teams
* Ability to skillfully enumerate a business problem, quantifies its impact, size relevant data, and document applicable sources
* Design and create data pipelines using modern engineering methods like streams and APIs that support objectives and meet SLAs
* Effectively measure data throughput from machine learning, and benchmark against KPIs to mitigate risks, provide transparency, and identify opportunities
* Take full accountability of data analysis and developed systems, and present a clear, accurate interpretation of results to the business
* Effectively manages expectations with stakeholders throughout analysis and development
* Balances own workload, deliverables, and milestones with autonomy, but also proven experience working in a team environment
* Leverage in-house, external and other open source machine learning software/algorithms;
* Research and apply superior data and methodology for the models;
* Perform ongoing monitoring of the models;
* Present model performance and insights to business leaders

Requirements:

* M.B.A. or Master's or Ph.D. in Computer Science, Statistics
* 3 or more years with noSQL unstructured data stores (Hadoop, MongoDB, Neo4j, ElasticSearch, etc.)
* 3 or more years working with languages such as R, Python, Scala, SQL, or Java
* 2 or more years with modern data engineering like kafka, spark, ETL, APIs, feedback loops, web triggers or tagging
* 2 or more years applying statistics in data analyses, regression modeling, econometrics, classification labeling, recommendation, parametric/non-parametric modeling, linear algebra, or econometrics