Associate Fraud Strategy Data Scientist

Bill.com Bill.com · Fintech · San Jose, CA · Data Science and Analytics

Associate Fraud Strategy Data Scientist at Bill.com, focusing on developing and executing fraud detection and risk mitigation strategies using data science and AI/ML techniques. The role involves building predictive algorithms, developing control strategies, and leveraging LLMs to enhance fraud prevention in a fintech environment.

What you'd actually do

  1. supporting key projects associated with fraud detection, risk analysis and loss mitigation at Bill.com
  2. design, creation, and execution of control strategies through direct work (complex analytical rule development, maintenance, etc) and in collaboration with Product Managers, Engineers, and Business Stakeholders
  3. Developed and maintained risk strategy frameworks for a domain to keep model strategy up to date with high performance with the goal of delivering on KPIs
  4. Built and deployed data driven and automated monitoring rules to detect and quickly respond to evolving risk trends
  5. Partnered with product/engineering on product/customer touchpoints for risk signal capture and treatments from strategies

Skills

Required

  • end to end fraud risk control strategy experience
  • eCommerce, or online payments industry experience
  • leveraging data science/analytics to solve complex business problems
  • design, creation, and execution of control strategies
  • complex analytical rule development, maintenance
  • Developed and maintained risk strategy frameworks
  • Built and deployed data driven and automated monitoring rules
  • Partnered with product/engineering on product/customer touchpoints for risk signal capture and treatments from strategies
  • Utilized advanced analytics techniques
  • building complex SQL/Python scripts with minimal guidance
  • interpreting results and using data findings to influence decision making
  • Developed flexible performance dashboards and monitoring
  • wrangling complex data in tools (ie. Tableau)
  • perform monitoring, diagnostic analytics, and share actionable stories with data
  • Applied advanced knowledge of data, metrics, profiles/typologies and key indicators in the financial fraud risk domain
  • find and recommend additional enhancements within data features, data enrichment, score recalibration for existing strategies and processes
  • Identify and execute new model/rules/product opportunities
  • Partnering and collaborating with cross functional teams including modeling, product/engineering, operations
  • design strategies across the lifecycle at multiple touchpoints
  • Establishing business requirements, shared KPIs, guiding execution, and performing validation/maintenance
  • Experience influencing cross functional team approaches
  • Mentorship and support of junior team members
  • Experience applying AI to accelerate data science work
  • designing prompts
  • rigorously evaluating outputs
  • integrating LLMs through APIs into notebooks and automated pipelines

Nice to have

  • experimental design
  • fraud typologies that involve onboarding fraud/abuse
  • data/control governance
  • proposal development
  • user acceptance definition
  • pre/post implementation validation
  • approval workflows

What the JD emphasized

  • fraud detection
  • risk analysis
  • loss mitigation
  • control strategies
  • data science
  • AI
  • LLMs

Other signals

  • fraud detection
  • risk analysis
  • loss mitigation
  • predictive algorithms
  • control strategies
  • data science
  • AI
  • LLMs