Senior Data Scientist

SoFi SoFi · Fintech · San Francisco, CA · Compliance

Senior Data Scientist role at SoFi focused on developing, optimizing, and validating Anti-Money Laundering (AML) models using machine learning and statistical methods. The role involves data quality assessment, model architecture design, ensuring regulatory compliance, and leading governance initiatives within the AML framework. It requires experience in the finance industry with BSA/AML or fraud modeling.

What you'd actually do

  1. Facilitate AML model development, implementation, optimization, assessment and validation of risk-based customer screening, transaction screening, transaction monitoring and AML customer risk rating covering multiple product lines, including banking, brokerage and lending to ensure sound risk coverage across the enterprise
  2. Maintain, test and configure AML vendor solutions to ensure conceptually sound design, proper implementation, and acceptable model performance.
  3. Research, compile and evaluate large sets of data to assess quality, integrity and completeness to determine suitability for AML model development.
  4. Architect and lead the design of advanced AML models utilizing machine learning and statistical modeling methods for supervised and unsupervised learning.
  5. Exercise flexibility in selecting model architectures, algorithms, third-party libraries, and development workflows, provided they align with project objectives and organizational requirements.

Skills

Required

  • Bachelor’s Degree or Master’s Degree in Statistics, Computer Science, Mathematics, Finance, Computer Science, Engineering or other relevant areas.
  • 3+ years of experience in the finance industry focusing on BSA/AML, OFAC, or fraud modeling/analytics.
  • Statistical/data analytical skills, including data quality validation, and predictive modeling experience in SQL and Python.
  • Knowledge of and ability to leverage traditional databases, cloud-based computing, and distributed computing.
  • Track record of leading AML governance-related initiatives, such as risk assessments, internal/external audits and other regulatory requirements.
  • Demonstrated ability to communicate effectively with all levels of the organization and across different business lines.

Nice to have

  • Knowledge of AML regulations and the USA PATRIOT Act.
  • Familiarity with regulatory guidance on Model Risk Management (Federal Reserve SR Letter 11-7, OCC Bulletin 2011-12, FDIC FIL 22-2017, DFS504)
  • Experience with data visualization (e.g., Tableau)
  • Experience with data monitoring systems (e.g., DataDog, Monte Carlo)
  • Experience with cloud data infrastructure (e.g., Snowflake)
  • Experience with automated transaction monitoring (e.g., Verafin)
  • Experience with customer/transaction screening (e.g., LexisNexis)
  • Experience with infrastructure automation software (e.g., Terraform)
  • Familiarity with virtualization and containerization (e.g., Docker)
  • Familiarity with container orchestration (e.g., Kubernetes)
  • CAMS certification preferred

What the JD emphasized

  • AML model development
  • model optimization
  • model validation
  • AML system integration
  • AML data infrastructure
  • AML data architecture
  • AML governance
  • risk assessments
  • internal/external inquiries
  • customer screening
  • transaction screening
  • transaction monitoring
  • customer risk rating
  • AML vendor solutions
  • machine learning
  • statistical modeling
  • supervised and unsupervised learning
  • AML compliance
  • regulatory requirements
  • ML framework
  • model risk management policies
  • internal model validation
  • external regulatory examinations
  • cross-functional approvals
  • development blockers
  • key stakeholders
  • governance documentation
  • tuning efforts
  • parameter changes
  • data validation
  • audit trail
  • tuning and optimization activities
  • model performance
  • management information dashboards
  • AML Risk Assessments
  • internal/external audit examinations
  • regulatory requirements
  • finance industry
  • BSA/AML
  • OFAC
  • fraud modeling/analytics
  • data quality validation
  • predictive modeling
  • SQL
  • Python
  • traditional databases
  • cloud-based computing
  • distributed computing
  • AML governance-related initiatives
  • risk assessments
  • internal/external audits
  • regulatory requirements
  • Model Risk Management (Federal Reserve SR Letter 11-7, OCC Bulletin 2011-12, FDIC FIL 22-2017, DFS504)

Other signals

  • model development
  • machine learning
  • statistical modeling
  • AML compliance
  • regulatory requirements