Staff Data Scientist

What you'll do

• Architect and own advanced modeling strategies across fraud and abuse problem domains (payment fraud, account takeover, identity spoofing, account abuse, content manipulation, credential stuffing)
• Drive framework selection—deciding when gradient boosting on velocity features suffices, when graph neural networks unlock network effects, when deep learning on sequence data catches adaptive fraud patterns
• Work backward from business metrics (customer adoption, chargeback reduction, operational lift) to model objectives informed by threat models
• Establish and defend model quality standards that account for adversarial dynamics
• Develop diagnostic frameworks to decompose model performance by fraud type, attacker sophistication level, geography, and temporal patterns
• Own the post-launch monitoring process, identify when degradation signals retrain vs. architecture change vs. active evasion by fraud rings
• Design sampling strategies that catch emerging fraud patterns before they scale
• Lead statistical innovation on highest-leverage fraud problems
• Explore novel feature representations drawn from understanding of fraud mechanics (network propagation of compromised accounts, timing signatures of automated attacks, behavioral deviation from account history)
• Run rigorous experiments to validate whether a suspected fraud pattern is exploitable or a false lead
• Publish findings internally (and externally where disclosable), and mentor junior data scientists
• Partner with ML engineering and information security on adversarial robustness
• Co-design models that resist manipulation; pressure-test feature importance against known evasion tactics
• Own the handoff from research to serving
• Build automated workflows that scale human expertise while respecting fraud complexity
• Leverage AI-assisted tools (LLMs, AutoML frameworks) to accelerate experimentation while maintaining verification checkpoints informed by domain knowledge

What will make you a strong fit

• Deep, hands-on knowledge of fraud and information security patterns
• Modeled payment fraud, account takeover, identity abuse, or network attacks in production
• Understand attacker incentives, exploit chains, evasion tactics, and how fraud patterns evolve in response to defenses
• 5+ years of hands-on modeling experience with production accountability
• Shipped models to millions of users, owned their performance in production
• Deep expertise in multiple modeling paradigms: Tree-based methods (XGBoost, LightGBM), deep learning architectures (CNNs, RNNs, transformers for sequential/graph data), and graph-based methods (GNNs, message passing, network propagation)
• Advanced degree in Statistics, Data Science, Machine Learning, or equivalent (MS or PhD in quantitative field, or 8+ years of demonstrable statistical modeling depth in production fraud/security contexts)
• Lean, deep statistical intuition informed by domain reality
• Proven ability to partner with AI-assisted automation tools (LLMs, AutoML)
• Comfort working in ambiguity and adversarial contexts