Senior ML Engineer — Fraud Detection at Scale

Plaid; San Francisco (CA); Vor Ort; USD 170.000 - 240.000; Vollzeit

Benefits dieser Stelle

Equity

401(k)

Medical/dental/vision

Zusammenfassung

Plaid’s Fraud Data team builds ML systems powering fraud detection across Plaid’s network. As a Senior Machine Learning Engineer, you will develop models, identify predictive patterns, and lead projects from experiments through deployment.

Responsibilities include building training data and features, tackling challenges such as label quality and data leakage, and deploying models in collaboration with Engineering and Data Science teams. Strong ownership and fintech context are valued.

Qualifikationen

• 7+ years of professional experience in ML, applied science, or software engineering for ML.
• Hands‑on experience designing, training, tuning, deploying models, and measuring production improvements.
• Strong ML and statistical fundamentals: feature engineering, experiment design, model evaluation, diagnostics.

Aufgaben

• Investigate fraud patterns and model errors to identify new signals and improve detection.
• Develop training datasets and features, address label quality and data leakage.
• Design, train, and tune models using traditional and modern ML methods (GBMs, neural nets).
• Design experiments to compare features and models across time periods and customer segments.
• Build data and training pipelines for reproducible experiments and efficient iteration.
• Deploy models in collaboration with Engineering and ML Infrastructure.
• Lead ML projects from open-ended problems through model release with cross-functional teams.
• Build ML expertise across the full lifecycle.

Kenntnisse

Python

SQL

PyTorch

scikit-learn

XGBoost

Model deployment

ML fundamentals

Tools

ML frameworks

Jobbeschreibung

Plaid’s Fraud Data team builds ML systems powering fraud detection across Plaid’s network. As a Senior Machine Learning Engineer, you will develop models, identify predictive patterns, and lead projects from experiments through deployment.

Responsibilities include building training data and features, tackling challenges such as label quality and data leakage, and deploying models in collaboration with Engineering and Data Science teams. Strong ownership and fintech context are valued.