Lead Data Scientist

About the role

Suits someone who has run models in production and wants to own the engineering standards around them. The team handles sensitive consumer data, so secure and compliant design matters as much as model quality.

At a glance

What you will do

• Build and maintain Python pipelines that clean and transform large datasets into features for modeling.
• Add data quality checks and validation so models and analyses can be trusted.
• Develop models for propensity, churn, segmentation and forecasting, from framing to evaluation.
• Deploy models to AWS for batch and real-time scoring, watch for drift and automate retraining.
• Design and evaluate LLM prompts, and wire generative AI into existing applications.

What they look for

• Strong Python for data work and ML, including pandas, NumPy, scikit-learn and PySpark, and comfort in Jupyter notebooks.
• Experience building pipelines on Spark, Redshift or similar, with expert SQL for complex queries on large datasets.
• Experience operationalizing models with SageMaker, MLflow, Docker or similar, and running workloads on AWS services like S3, Glue, Lambda or

Benefits

• An inclusive culture built on owning your work, serving customers well and earning respect.