Lead Data Scientist
Zeeshan AhmadUnited StatesLEADPosted 1h ago
PythonPySparkAdvanced SQLDatabricksGitSnowflake
About the Role
We are seeking a Lead Data Scientist with expertise in Databricks and predictive modeling to join our team in Seattle, WA. This is a long-term contract position requiring local candidates only.
Key Responsibilities
• Optimize Databricks performance through partitioning, Delta optimization, and cluster sizing
• Develop predictive models focusing on binary classification and churn prediction
• Implement solutions using Python, PySpark, and Advanced SQL
• Apply statistical methods and develop composite scores, indices, and scorecards
• Maintain production-grade code with Git and version control
Requirements
• Strong hands-on experience with Python, PySpark, and Advanced SQL
• Expertise in Databricks performance optimization
• Strong understanding of applied statistics and predictive modeling
• Experience with Git, version control, and production-grade coding practices
• Excellent documentation, analytical thinking, and data validation skills
• Wireless/Telecom domain knowledge and network KPIs
• Snowflake experience
• Experience with Weight of Evidence (WoE) / Information Value (IV)