We’re hiring a versatile, hands-on Data Scientist to build and improve predictive models that support marketing and customer engagement, and to strengthen how models and data workflows move from development into reliable, repeatable production processes. You’ll combine strong statistical/Machine Learning skills with practical engineering habits—writing maintainable code, improving reproducibility, and partnering across teams to turn analysis into measurable business impact. Experience improving existing workflows and delivering pragmatic automation is highly valued.

Responsibilities:

Predictive modeling & decision support

• Develop and validate response, premium, and other predictive models to improve targeting and profitability for direct mail and online campaigns.
• Build omnichannel optimization and personalization models to determine who should receive which offer/message, through which channel, and when, to maximize campaign performance and profitability.
• Analyze historical customer and marketing data to identify trends and patterns that inform strategy and optimization.
• Design tests/experiments to evaluate campaign parameters (e.g., pricing, coverage, response, creative) and quantify lift and impact.

Production-ready analytics & ML

• Build new and upgrade existing pipelines for data flow, business processes, scoring, and reporting (batch-first, designed for scale).
• Contribute to model delivery patterns such as scheduled scoring jobs, APIs, or containerized services, including lightweight monitoring and versioning.

• MS or PhD in a quantitative field (e.g., Data Science, Computer Science, Mathematics, Statistics, or related field); regardless of degree, demonstrated experience delivering predictive models in production-like environments
• At least 1-3 years of experience
• Strong experience in Python and/or R for analysis, modeling, and building repeatable workflows (Python preferred for production use cases).
• Demonstrated ability to build predictive models using statistical and machine learning techniques.
• Strong SQL and experience working with warehouse-style data structures and/or analytics datasets.
• Ability to work effectively with ambiguous requirements and real-world data quality constraints while still delivering dependable results. Experience with cloud computing (AWS/Azure/GCP) for data processing or model deployment.
• Solid communication skills—able to explain assumptions, tradeoffs, and results to both technical and non-technical audiences.
• Familiarity with orchestration / pipelines (e.g., Airflow/Prefect/Dagster) and CI/CD practices for data or ML workflows preferred
• Exposure to model lifecycle management concepts (e.g., model versioning, basic monitoring, and maintaining reproducible training/scoring workflows) preferred.