Data Scientist, Risk & Fraud

Whatnot · Consumer · San Francisco, CA · Engineering

Data Scientist focused on risk and fraud detection for a livestream shopping platform. The role involves translating data into actionable recommendations, defining KPIs, analyzing existing methods, partnering with ML engineers to develop anti-fraud practices, designing and evaluating experiments, developing causal inference frameworks, building data products, and collaborating cross-functionally to shape fraud strategy. Requires advanced SQL, Python/R, A/B testing, and causal inference experience.

What you'd actually do

  1. Translate complex data into actionable recommendations for the Fraud engineering and operations teams.
  2. Define and own the KPIs that measure the cost of fraud, strategies to prevent it, and impact to users and marketplace performance.
  3. Analyze the effectiveness of existing methods and partner with product and machine learning engineers to develop better anti-fraud practices.
  4. Partner with product managers, engineers, and operations teams to design, implement, and evaluate feature rollouts to combat bad actors on the platform.
  5. Define and own the experimentation playbook for Fraud at Whatnot.

Skills

Required

  • Advanced SQL
  • Python or R for data analysis, modeling, and experimentation
  • Experience designing and analyzing A/B tests
  • Understanding of causal inference techniques
  • Strong data visualization skills
  • Familiarity with BI tools
  • 5+ years of experience in the Data field
  • 3+ years of experience in Data Analytics & Science supporting anti-fraud, risk, trust & safety, or integrity problems
  • Experience with modern data warehouses (Snowflake, BigQuery, Redshift)
  • Experience with tools like Spark or DBT

Nice to have

  • equivalent work experience

What the JD emphasized

  • anti-fraud
  • risk
  • fraud
  • bad actors
  • fraudulent actors
  • fraud vectors
  • anti-fraud practices
  • fraud strategy
  • fraud domains

Other signals

  • fraud detection
  • risk management
  • machine learning models
  • experimentation
  • causal inference