Staff Data Scientist

Sift • ,

6d • $195,000 - $265,000

About The Position

Our Data Science team owns the machine learning backbone of Sift's fraud platform—a system that learns from 1T+ events annually across our network of 700+ global customers. You'll work alongside ML engineers, platform teams, and customer success leads who obsess over reducing false positives while catching sophisticated fraud patterns at scale. We're looking for a specialist who combines exceptional statistical rigor with deep fraud and information security domain expertise. You understand account takeover tactics, payment fraud vectors, identity manipulation, and network abuse patterns—not from reading threat reports, but from having modeled them in production. You'll be the go-to expert for diagnosing why models fail, architecting solutions across multiple modeling paradigms, and building processes that prevent data science from becoming a bottleneck. Your domain knowledge becomes a force multiplier: you'll spot feature opportunities others miss, anticipate how adversaries will probe your models, and translate customer fraud signals into modeling advantage. Success looks like: Models that outperform baseline by measurable margins because you engineered features informed by years of fraud pattern understanding. Production systems that don't degrade and don't leak money to evolving fraud schemes. Teams that trust your framework recommendations because you've debugged production failures in real fraud contexts. A research program that uncovers untapped signal in our customer data while staying ahead of attacker sophistication.

Requirements

• Deep, hands-on knowledge of fraud and information security patterns. You've modeled payment fraud, account takeover, identity abuse, or network attacks in production.
• 5+ years of hands-on modeling experience with production accountability.
• Deep expertise in multiple modeling paradigms: Tree-based methods (XGBoost, LightGBM with parameter mastery), 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.
• Comfort working in ambiguity and adversarial contexts.

Nice To Haves

• Some of that experience comes from adversarial or security-adjacent domains.
• You know when each is overfit versus underspecified. You've chosen frameworks based on problem structure, not trend.
• You should reason naturally about confidence intervals, bias-variance tradeoffs, and statistical significance—not just memorize formulas. We care more about statistical intuition + proven execution than pedigree.
• You can explain why a fraud model is failing through first principles (feature leakage from attacker behavior that changed, distribution shift from geography expansion, optimization pathology from class imbalance).
• You use LLMs, AutoML, and other AI systems to move faster—especially for feature engineering exploration and pattern discovery—but you verify their outputs and know where they hallucinate or oversimplify.
• You don't wait for perfect specs—you clarify what "reducing fraud leakage" means for a specific customer, run a small experiment, present findings with uncertainty bands, and iterate.
• You're comfortable saying "attackers might exploit this assumption" or "we need more data on this vector."
• You're comfortable saying "this is a business decision about fraud tolerance, not a modeling decision."

Responsibilities

• Architect and own advanced modeling strategies across fraud and abuse problem domains (payment fraud, account takeover, identity spoofing, account abuse, content manipulation, credential stuffing).
• Establish and defend model quality standards that account for adversarial dynamics.
• Lead statistical innovation on our highest-leverage fraud problems.
• Partner with ML engineering and information security on adversarial robustness.
• Build automated workflows that scale human expertise while respecting fraud complexity.

Benefits

• Diversity drives innovation, equity is a fundamental right, and inclusion is a basic human need.
• A place where all Sifties feel secure sharing their authentic selves and diverse experiences with their teams, their customers, and their community – ultimately using this empowerment and authenticity to build trust and create a safer Internet.

What This Job Offers

• Job Type: Full-time
• Career Level: Senior