- Company Name
- Whatnot
- Job Title
- Machine Learning Engineer, Fraud
- Job Description
-
Job title: Machine Learning Engineer, Fraud
Role Summary: Design, train, deploy, and maintain machine‑learning and LLM models that detect and prevent fraudulent activity across users, payments, and marketplace interactions, while balancing security and user experience.
Expectations: 2–6 years of ML or software engineering experience, preferably in risk, fraud, or trust & safety. Strong Python proficiency with scikit‑learn, PyTorch, LightGBM. Backend development skills and proven ability to deploy ML models to production. Experience with data pipelines, SQL, Spark, DBT, and orchestration frameworks (Dagster, Kubeflow). Knowledge of fraud detection techniques such as anomaly detection, chargeback prediction, and graph‑based modeling. Bachelor’s degree in Computer Science, related field, or equivalent work experience.
Key Responsibilities:
• Architect and implement end‑to‑end fraud detection systems, including model training, deployment, and monitoring.
• Build intelligent user graphs and collusion models to capture behavioral patterns.
• Develop scalable, low‑latency data pipelines and real‑time inference systems.
• Perform deep behavioral and adversarial analysis to identify fraud trends.
• Collaborate with Trust & Safety, Payments, and Infrastructure teams on labeling, feature design, and evaluation pipelines.
• Implement drift detection, model monitoring, and risk orchestration combining rules, models, and heuristics.
• Define, track, and report key fraud metrics (precision, recall, false‑positive rate, latency).
• Continuously update systems to counter emerging fraud tactics.
Required Skills:
• Python, scikit‑learn, PyTorch, LightGBM, TensorFlow/other ML frameworks.
• Backend development (Java, Go, or similar preferred).
• Data engineering: SQL, Spark, DBT, data orchestration (Dagster, Kubeflow).
• Graph analytics and anomaly detection techniques.
• Feature store design and use.
• Strong analytical skills and ability to translate business risk into measurable ML solutions.
Required Education & Certifications:
• Bachelor’s degree in Computer Science, Data Science, Engineering, or related field, or equivalent professional experience.