AVP, Sanctions Model Design & Risk (Hybrid)

State Street; Princeton (NJ); Hybrid; USD 80,000 - 140,000; Full time

Benefits offered by this job

401K match

Paid time off

Volunteer days

Job summary

State Street is seeking a Sanctions Analyst, AVP, to lead design, validation, and risk management of sanctions screening models within FCC. This role blends compliance, technology, and quantitative analytics to ensure robust, well-governed models aligned with evolving regulations.

Hybrid work with in-office presence; strong Python/SQL skills, ML/NLP capabilities, and experience in model risk management are essential for ongoing governance and performance optimization.

Qualifications

• Bachelor’s or Master’s degree in related quantitative/technical field.
• 6+ years in financial crime compliance or related areas.
• Experience designing, reviewing, validating sanctions screening apps and models, including performance monitoring.
• Strong quantitative/analytical skills with ML/NLP/Entity Resolution knowledge.
• Proficiency in Python and SQL for data analysis and automation.
• Experience with cloud-based data environments and governance.

Responsibilities

• Own sanctions screening models and act as FCC-IT liaison for day-to-day operations.
• Monitor model performance, thresholds, and tuning; coordinate remediation with tech teams.
• Support data quality, list management, and model configuration for sanctions screening.
• Oversee monitoring of outputs, alert volumes, and risk distributions amid business growth.

Skills

AI/ML expertise

Python

SQL

Sanctions screening

Watchlist management

Agile environments

Problem solving

Education

Bachelor’s or Master’s degree in Data Science, CS, Stats, Eng, Finance

Tools

Databricks

Pandas

NumPy

scikit-learn

SQL

Python

Job description

State Street is seeking a Sanctions Analyst, AVP, to lead design, validation, and risk management of sanctions screening models within FCC. This role blends compliance, technology, and quantitative analytics to ensure robust, well-governed models aligned with evolving regulations.

Hybrid work with in-office presence; strong Python/SQL skills, ML/NLP capabilities, and experience in model risk management are essential for ongoing governance and performance optimization.