Senior Associate, AML Model Development

StrategyBRIX is a boutique consulting firm supporting fintechs, crypto businesses, and financial institutions through complex AML and financial crime compliance challenges. Our work sits across regulation, technology, and operations.

We are seeking a Senior Associate with strong technical and machine learning experience to join our consulting practice and deliver detection solutions for clients across fintech, banking, and crypto. This is a remote role based in either Canada or the US, working closely with senior leadership, compliance experts, and client stakeholders to turn regulatory requirements into production-ready model capabilities. This role suits someone who works comfortably across data science and financial regulation, understands a client's risk landscape and technical constraints, and builds models that strengthen their defenses against financial crime. You should be comfortable writing code, documenting model methodology, and advising clients on how to operationalize your solutions after the engagement ends.

What you will do You will serve as a technical expert on client engagements, designing and building models that help financial institutions detect and prevent financial crime. Working across a portfolio of clients, from fintechs to crypto exchanges, you will assess their risk environments, regulatory obligations, and technical landscapes to deliver AML and fraud detection capabilities tailored to each. Your work will span the full project lifecycle, from discovery and solution design through model development, validation, tuning, and knowledge transfer to client teams.

Lead technical workstreams focused on transaction monitoring, sanctions screening, customer risk rating, and suspicious activity detection. Tune transaction monitoring systems, including threshold setting, segmentation, and above-the-line and below-the-line testing. Conduct assessments of clients' existing AML and fraud model environments and provide actionable recommendations for enhancement. Design, develop, and tune models suited to each client's data infrastructure, risk appetite, and regulatory requirements. Engineer features from transactional, behavioral, and entity data, including feature selection and treatment of class imbalance common in financial crime data. Select and compare modeling approaches, from gradient-boosted trees and other supervised methods to unsupervised and anomaly-detection techniques, and justify the choice for each use case. Train, tune, and evaluate models using appropriate metrics for rare-event detection, such as precision, recall, ROC-AUC, and precision-recall curves, with attention to the false-positive burden on investigation teams. Test and validate models, including out-of-time and out-of-sample testing, stability analysis, and benchmarking against existing rules or champion models. Build scalable pipelines that adapt to varying client technology stacks and data maturity levels. Create comprehensive model documentation that satisfies regulatory expectations and client model risk management standards. Present technical findings and recommendations to client stakeholders, from data science teams to senior compliance leadership. Mentor junior consultants on development best practices and financial crime domain knowledge. Contribute to internal firm initiatives, including reusable model frameworks, business development, and thought leadership.

What we are looking for 5+ years of experience developing models, machine learning or statistical, in a professional environment. 3+ years of experience in financial crime, AML, fraud detection, or a related compliance domain. Strong proficiency in Python and SQL, including ML libraries such as scikit-learn, XGBoost, or LightGBM. Hands-on experience across the machine learning lifecycle: feature engineering and selection, model selection, training and hyperparameter tuning, and testing and validation. Sound grasp of evaluation for imbalanced, rare-event problems, including the trade-off between detection rate and false positives. Familiarity with transaction monitoring tuning and model risk management expectations. Demonstrated consulting experience or client-facing delivery in a professional services environment. Excellent communication skills, with the ability to translate technical concepts for non-technical audiences. Bachelor's degree in computer science, statistics, mathematics, or a quantitative field.

Nice to have Prior experience at a consulting firm, Big Four, or specialized financial crimes advisory practice. Experience with deep learning frameworks such as TensorFlow or PyTorch, or with graph-based methods for network and entity analysis. Solid understanding of AML regulatory frameworks, including BSA, FATF guidelines, and FinCEN requirements. Experience with formal model validation under model risk management frameworks in a regulated environment. Exposure to blockchain analytics tools, for example, Chainalysis, Elliptic, or TRM Labs, for crypto and digital asset clients. Background in explainable AI techniques and their application in regulated environments. Advanced degree in a quantitative discipline.

Why StrategyBRIX As a boutique, we offer direct client exposure, varied technical work across fintech and crypto, and close proximity to senior leadership, without the layers of a large firm. You build models that go into production, not slide decks.