Applied Scientist, Minerva
Core
Build and maintain risk detection models for Kindle Direct Publishing and Kindle Unlimited to prevent fraud, abuse, and harmful content.
Role type
Applied Scientist (Risk Science)
Builds
Production ML models for content risk, fraud, and abuse prevention
Domain
Books publishing, content moderation, trust and safety
Deliverable
production ML models
Required skills
model monitoring, data drift detection, graph-based ML, behavioral modeling, anomaly detection, large-scale data processing, generative AI tools, Java, C++, Python, algorithms and data structures, numerical optimization, data mining, parallel and distributed computing
Preferred skills
patents or publications at top-tier peer-reviewed conferences or journals, experience in fraud detection, abuse prevention, trust and safety, or content moderation
Technologies
Spark, SQL
Responsibilities
Monitor production risk models and push their quality higher, Design, train, and evaluate improved detection models, Build datasets, labels, evaluation sets, and metrics, Write clear readouts with recommendations for scientists, engineers, and policy partners
Seniority
Mid-Senior, hands-on IC