About the Role
You will use modern AI tools including Claude and other LLM based agents to automate significant portions of oversight monitoring and documentation work turning a manual documentation heavy function into a scalable program. You will partner with Machine Learning Engineering and BSA AML Policy Teams to provide end to end technical oversight effective challenge and ongoing monitoring throughout the model development lifecycle. You will design human in the loop checkpoints so that automated outputs remain defensible to regulators and independent monitors. You will lead ongoing monitoring by designing and developing real time dashboards to monitor model health including input data monitoring and ongoing model performance. You will set standards for threshold tuning and ongoing Below the Line BTL testing controls. You will establish frameworks and triggers for identifying when model performance is degrading and requires tuning or deprecation. You will provide end to end oversight of model development including transaction monitoring models heuristic and rules based detection logic and the data pipelines that feed alerts. You will oversee blockchain analytics and screening tools such as Chainalysis and TRM Labs with attention to typology coverage alert quality and integration with downstream investigations. You will oversee Sanctions Screening models including list management fuzzy match tuning and false positive reduction. You will oversee Customer Risk Scoring models including segmentation logic periodic recalibration and effective challenge of risk drivers. You will oversee the design and validation of AI driven case resolution including LLM based and ML based models that triage enrich or disposition alerts ensuring decisions are explainable auditable and defensible to regulators.
Requirements
- 7+ years of experience in compliance technology at regulated financial institutions or as a consultant working with financial institutions
- Hands on experience building with modern AI tools including Claude GPT or comparable LLM based agents and a track record of using them to automate work in production
- Experience with both Machine Learning and Heuristic models across Transaction Monitoring Sanctions Screening and Customer Risk Scoring
- Experience with input data quality monitoring
- Experience with model performance monitoring
- Experience conducting AML model validations aligned with SR 11-7 and OCC 2011-12
- Experience responding to examinations and consent orders and working with regulators and independent monitors
- Experience with virtual currencies
- Familiarity with blockchain analytics and screening tools such as Chainalysis and TRM Labs
- A track record of driving cross functional initiatives
- A working understanding of regulated financial services and compliance obligations
- Familiarity with statistical concepts related to machine learning
- Expertise in data analytics and visualization
Responsibilities
- Build with Modern AI Tools: Use AI agents including Claude and other LLM based tools to automate oversight monitoring and documentation including drafting requirements exam ready documentation data quality monitoring and ongoing model performance reporting
- Design human in the loop checkpoints so that automated outputs remain defensible to regulators and independent monitors
- Establish and maintain model and data governance frameworks aligned with SR 11-7 SR 26-2 and OCC 2011-12 so engineering teams can ship defensible models at pace and provide effective challenge to the BSA AML Policy Team
- Lead ongoing monitoring by designing and developing real time dashboards to monitor model health including input data monitoring and ongoing model performance
- Set standards for threshold tuning and below the line testing controls
- Establish frameworks and triggers for identifying when model performance is degrading and requires tuning or deprecation
- Provide end to end oversight of model development including transaction monitoring models heuristic and rules based detection logic and the data pipelines that feed alerts
- Oversee blockchain analytics and screening tools such as Chainalysis and TRM Labs and ensure integration with downstream investigations
- Oversee sanctions screening models including list management fuzzy match tuning and false positive reduction
- Oversee customer risk scoring models including segmentation logic periodic recalibration and effective challenge of risk drivers
- Oversee the design and validation of AI driven case resolution including LLM based and ML based models that triage enrich or disposition alerts ensuring decisions are explainable auditable and defensible to regulators
Benefits
- Remote work
- Medical insurance
- Flexible time off
- Retirement savings plans
- Modern family planning