Data Scientist

isolved • Sandy, UT

1d

About The Position

Data Scientist Summary/objective We are seeking a highly skilled Data Scientist to focus on building and deploying predictive models that identify customer churn risk and upsell opportunities. This role will play a key part in driving revenue growth and retention strategies by leveraging advanced machine learning, statistical modeling, and large-scale data capabilities within Databricks. Why Join Us? Be at the forefront of using Databricks AI/ML capabilities to solve real-world business challenges. Directly influence customer retention and revenue growth through applied data science. Work in a collaborative environment where experimentation and innovation are encouraged.

Requirements

• Master's or PhD in Data Science, Statistics, Computer Science, or related field (or equivalent industry experience).
• 3+ years of experience building predictive models in a production environment.
• Strong proficiency in Python (pandas, scikit-learn, PySpark) and SQL.
• Demonstrated expertise using Databricks for: Data manipulation and distributed processing with PySpark . Building and managing models with MLflow . Leveraging Delta Lake for efficient data storage and retrieval. Implementing scalable ML pipelines within Databricks' ML Runtime.
• Experience with feature engineering for behavioral and transactional datasets.
• Strong understanding of customer lifecycle analytics, including churn modeling and upsell/recommendation systems.
• Ability to communicate results and influence decision-making across technical and non-technical teams.
• Employees must be legally authorized to work in the United States.

Nice To Haves

• Experience with cloud platforms (Azure Databricks, AWS, or GCP).
• Familiarity with Unity Catalog for data governance and security.
• Knowledge of deep learning frameworks (TensorFlow, PyTorch) within Databricks.
• Exposure to MLOps best practices (CI/CD for ML, model versioning, monitoring).
• Background in SaaS, subscription-based businesses, or customer analytics.

Responsibilities

• Model Development Design, develop, and deploy predictive models for customer churn and upsell propensity using Databricks ML capabilities.
• Evaluate and compare algorithms (e.g., logistic regression, gradient boosting, random forest, deep learning) to optimize predictive performance.
• Incorporate feature engineering pipelines that leverage customer behavior, transaction history, and product usage data.
• Data Engineering & Pipeline Ownership Build and maintain scalable data pipelines in Databricks (using PySpark, Delta Lake, and MLflow) to enable reliable model training and scoring.
• Collaborate with data engineers to ensure proper data ingestion, transformation, and governance.
• Experimentation & Validation Conduct A/B tests and back testing to validate model effectiveness.
• Apply techniques for model monitoring, drift detection, and retraining in production.
• Business Impact & Storytelling Translate complex analytical outputs into clear recommendations for business stakeholders.
• Partner with Product and Customer Success teams to design strategies that reduce churn, increase upsell and improve customer retention KPIs.

What This Job Offers

• Job Type: Full-time
• Career Level: Mid Level