DATA SCIENTIST

Sally Beauty•Plano, TX

2d•$100,000 - $120,000•Hybrid

About The Position

We are seeking a hands-on Data Scientist to build the models and data products that power how SBH understands and activates its customers. This is a technical individual-contributor role for a data scientist who is equally comfortable engineering a feature pipeline in Databricks, defending a model's validation approach, and explaining the resulting business recommendation to a non-technical stakeholder. Your mission is to increase Customer Lifetime Value (CLV) by developing the predictive assets behind hyper-personalized CRM campaigns, retention strategies, and proactive churn reduction. You will own models end to end, from problem framing and feature engineering through training, validation, deployment, and ongoing performance monitoring, and ensure they run reliably in production rather than living in a notebook. This role sits at the intersection of advanced analytics and commercial strategy and is critical to advancing SBH's Understand & Activate Customer agenda. You will work closely with Data Engineering, CRM, Marketing, and Merchandising partners, and will help mature our Databricks environment from a place where analysis happens into a platform that delivers repeatable, monitored, production-grade customer intelligence.

Requirements

Master’s degree in mathematics / Statistics/Data Science and Analytics, Computer Science, Economics, Physics, or a related field required.
4+ years of hands-on experience in data science, applied machine learning, or customer analytics.
Advanced proficiency in Python (pandas, NumPy, scikit-learn) and SQL. Experience with R is a plus.
Hands-on experience with Databricks, Spark/PySpark, Delta Lake, and a major cloud environment (Azure preferred; AWS/GCP acceptable).
Regression, classification, clustering (K-Means), tree-based and boosting methods, survival analysis, recommender systems, and dimensionality reduction (PCA). Exposure to deep learning frameworks is a plus.
Solid grounding in hypothesis testing, confidence intervals, experimental design, cross-validation, and basic probability and linear algebra.
Experience with model deployment and monitoring (e.g., MLflow), model re-training automation, drift detection, version control (Git), and code review practices. Exposure to REST APIs, containerization, or orchestration tooling is a plus.
Strong PowerPoint and Excel skills, with the ability to build an executive-ready narrative.
Ability to “connect the dots” across disparate data points to form a cohesive business recommendation.
A self-starter who operates independently, seeks opportunities to scale and automate, is comfortable challenging the status quo, and can present findings credibly to non-technical senior leadership.
Outstanding organizational skills and dedication to quality and integrity, with the ability to contribute effectively in a fast-paced environment.

Nice To Haves

Master's degree preferred.
Experience in Retail, CPG, e-commerce, or subscription/loyalty-driven businesses is highly desirable.
Experience with R is a plus.
AWS/GCP acceptable.
Exposure to deep learning frameworks is a plus.
Exposure to REST APIs, containerization, or orchestration tooling is a plus.

Responsibilities

Build machine learning models through all phases of development, design, feature engineering, training, evaluation, validation, and implementation, using Python. Core use cases include churn and retention modeling, propensity-to-buy, CLV prediction, customer persona/segmentation, and next-best-action recommendations.
Move beyond basic demographics to build behavioral, psychographic, and value-based segments (e.g., RFM, K-Means clustering, propensity tiers) that CRM and Marketing can activate directly.
Apply Market Basket Analysis (MBA), survival analysis, uplift/incrementality modeling, and recommender approaches to uncover cross-sell, up-sell, and hidden revenue opportunities.
Produce summary statistics, distribution and correlation studies, and disciplined feature selection; apply confidence intervals, cross-validation, and appropriate model performance validation to every deliverable.
Prioritize and deliver critical ad hoc analysis supporting the SALLY plan and forecast, balancing speed with statistical accuracy.
Develop and maintain the customer 360 view and supporting data pipelines in Databricks using Python, PySpark, and SQL. You should be comfortable building your own pipelines to enable your analysis rather than waiting on others.
Convert proof-of-concept code into production-ready, re-usable components integrated into products and services, with attention to scalability (compute, memory, I/O, model serialization, caching).
Automate ML processes such as scheduled scoring and model re-training, and implement monitoring for data drift, model drift, and accuracy degradation. Contribute to impact assessment, back-testing, explainability, reproducibility, and data quality checks.
Follow source control, peer code review, and automated testing practices (Git/Azure DevOps); contribute to CI/CD for analytics assets.
Design and analyze A/B and multivariate tests for email, SMS, push, and in-app campaigns to optimize engagement, conversion, and incremental lift.
Build statistically sound test and control audiences in partnership with CRM, ensuring balance, mutual exclusivity, and reproducibility.
Execute the Test vs. Control measurement framework and apply guardrails for attribution, incrementality, and performance readouts.
Apply and help maintain Standard Operating Procedures (SOPs) for customer campaign measurement, reporting hygiene, and data integrity.
Support data-driven customer journeys (Onboarding, Growth, Retention, Reactivation) with the models and audiences that make them work.