A Machine Learning Engineer specializes in designing, building, and deploying machine learning models. They utilize statistical and mathematical techniques, parallelizing processing, hyperparameter tuning, and other optimization methodologies to improve model performance. Responsibilities also include collecting and preprocessing large datasets, conducting exploratory data analysis, working closely with data engineers to understand data requirements, and engineer input variables for machine learning models.
Onsite in Boston or Quincy or Burlington in Massachusetts - 4 days onsite
Duration:
12 months
Pay:
60-65 Responsibilities Develop, test, and enhance machine learning and advanced analytics models supporting AML, sanctions screening, transaction monitoring, and alert prioritization. Perform hands-on data analysis using large transactional and reference datasets to identify patterns, anomalies, and risk indicators related to financial crime. Support feature engineering activities, including data exploration, feature selection, and transformation to improve model performance and stability. Train, evaluate, and tune models using appropriate techniques and performance metrics, including precision, recall, and false-positive reduction. Assist in validating model outputs by analyzing false positives, false negatives, and alert quality in partnership with compliance and operations teams. Contribute to model documentation, including assumptions, methodologies, limitations, and performance results, to support audit and regulatory review. Support ongoing model monitoring and performance tracking, identifying drift, degradation, or data quality issues and recommending remediation. Work with data engineering teams to understand data pipelines, resolve data issues, and ensure model inputs remain accurate and reliable. Participate in Agile delivery processes, contributing to user stories, testing activities, and release support for AI/ML solutions. Support User Acceptance Testing (UAT) by validating model behavior against business and compliance expectations. Stay current on emerging AI/ML techniques, open-source tools, and industry trends relevant to financial crime and compliance analytics. Translate complex ideas into cogent business requirements documents. Create BRDs and data mapping documents. Collaborate with cross-functional teams to identify requirements, provide guidance, ask and respond to questions, and assist with resolving complex issues. Ensure that any gaps identified in the BRD are addressed and rectified by the relevant team. Support development and testing teams by answering questions and updating documentation as needed based on feedback. Be responsible for communication, resolution, and potential escalation of critical issues. Work with the Project Manager and Product Owner to create and manage user stories using Jira. Support the team in triaging issues found during testing. Work in a complex, deadline-driven organization on projects with minimal supervision. Analyze complex problems, derive options and solutions, and present them in an understandable manner to stakeholders, developers, testers, and users at multiple levels.
Must-Have Skills:
Experience with machine learning, advanced analytics, model development, evaluation, tuning, and monitoring. Strong hands-on data analysis and feature engineering experience using large transactional and reference datasets. Knowledge of AML, sanctions screening, transaction monitoring, alert prioritization, and financial crime analytics. Experience analyzing model performance, including precision, recall, false positives, false negatives, alert quality, drift, and data quality. Proficiency creating BRDs, data mapping documents, and user stories using Jira. Strong requirements gathering, documentation, problem-solving, and analytical skills. Experience working with cross-functional teams, including development, testing, data engineering, compliance, and operations. Experience supporting Agile delivery, UAT, testing, issue triage, resolution, and escalation. Ability to translate complex ideas and problems into clear business requirements and solutions and communicate them effectively to stakeholders at multiple levels. Ability to work independently in a complex, deadline-driven environment.
