Data Scientist

APPLE INC has the following available in Austin, Texas. Responsible for advanced statistical analysis using Python, with a specific focus on detecting fraud patterns and anomalies within the Apple Online Store. Extract precise data and analyses by crafting complex SQL queries, with a focus on impact to bottom-line. Build and utilize tools including Tableau for comprehensive trend analysis and reporting across LOBs. Recognize and create immediate problem-solving responses to emerging fraud patterns. Craft complex SQL queries for intricate fraud analysis, extracting nuanced insights from large datasets. Write complex queries for business problem understandings and make recommendations. Use advanced statistical modeling techniques for predictive fraud analytics. Design and apply statistical methods for impact assessment, ensuring a comprehensive data-driven approach. Build frameworks to perform A/B testing to understand the impact of experiments, with an aim to reduce overall losses and drive efficiency gains for investigators. Build statistical models to assess the impact of changes to the current internal routing system. Use python, SQL and airflow/Jenkins to build jobs that automate cross-LOB reporting. Analyze impact of current ML models in fraud investigator space and work with Machine Learning Engineers to aid in feature scoping. 40 hours/week. Master’s degree or foreign equivalent in Applied Mathematics, Math, Statistics, Engineering, Computer Science, Analytics, or a related field and 5 years of experience in the job offered or related occupation. 5 years experience is required for the following skills: Writing complex SQL queries in Snowflake, Trino, and Splunk to extract, transform, and combine structured and unstructured datasets for operational analysis and building recommendations. Building interactive, user-centric dashboards in Tableau that visualize trends, performance, and operational KPIs— empowering hundreds of users to make data-driven decisions in near real-time. Translating complex analytical results and model performance data into concise, compelling narratives and visualizations tailored to executive audiences — highlighting actionable insights and quantifiable opportunities for loss reduction and operational efficiency. Developing and scheduling automated reporting and analytics workflows using Jenkins and Apache Airflow, ensuring timely delivery of insights to operational teams. Leveraging Python, Pandas, and other data science tools to conduct bespoke analyses on patterns, automate anomaly detection, and quantify the efficacy of loss mitigation strategies. Proactively identifying high-impact operational improvements by mining data for emerging trends and workflow bottlenecks, then clearly communicating these opportunities to leadership with supporting data stories and ROI estimates, accounting for seasonality. Applying advanced forecasting techniques (time series, regression models) to predict change in workloads, enabling optimized resource planning and escalation management. Partnering closely with cross-functional teams (engineering, product, operations) to enhance data accessibility and transparency, driving better decision-making and investigator effectiveness across the organization. Specialized in cloud cost optimization across AWS and Google Cloud Platform (GCP), systematically analyzing CPU, GPU, Kubernetes cluster, Redshift, and NAT Gateway usage to identify and execute cost-saving initiatives. Building optimization strategies leveraging reserved instance commitments, rightsizing, and workload redistribution, resulting in significant cloud spend reductions for enterprise clients. N/A

For more details click Job Post.