Senior Data Scientist (Predictive Analytics Focus & Databricks)

Design and deploy predictive models (e.g., forecasting, churn analysis, fraud detection) using Python/SQL, Spark MLlib, and Databricks ML

Build end-to-end ML pipelines (data ingestion feature engineering model training deployment) on Databricks Lakehouse

Optimize model performance via hyperparameter tuning, AutoML, and MLflow tracking

Collaborate with engineering teams to operationalize models (batch/real-time) using Databricks Jobs or REST APIs

Implement Delta Lake for scalable, ACID-compliant data workflows.

Enable CI/CD for ML pipelines using Databricks Repos and GitHub Actions

Troubleshoot issues in Spark Jobs and Databricks Environment.

Requirements:

5+ years in predictive analytics, with expertise in regression, classification, time-series modeling

Hands-on experience with Databricks Runtime for ML, Spark SQL, and PySpark

Familiarity with MLflow, Feature Store, and Unity Catalog for governance.

Industry experience in Life Insurance or P&C.

Skills:

Python, PySpark , MLflow , Databricks AutoML

Predictive Modelling ( Classification , Clustering , Regression , timeseries and NLP)

Cloud platform (Azure/AWS) , Delta Lake , Unity Catalog

Certifications:

Databricks Certified ML Practitioner

Data Science

BCM Industry

01/04/2025

Req. VR-113106