Senior Data Scientist - Customer Analytics

About the Company

Blend is an established AI services firm dedicated to creating significant value for clients by integrating data science, artificial intelligence, cutting-edge technology, and human expertise. The company’s goal is to empower ambitious projects by combining human talents with AI, fostering innovation and delivering data-driven insights across industries.

Job Overview

We seek a seasoned Senior Data Scientist to spearhead the development and implementation of sophisticated data science projects related to pricing optimization, customer segmentation, marketing analytics, Bayesian modeling, causal inference, and advanced optimization techniques. This hybrid role requires both technical mastery and leadership, involving mentorship, complex problem solving, client collaboration, and transforming analytical findings into actionable business strategies.

Key Responsibilities

• Manage the entire lifecycle of data science initiatives, including problem framing, exploratory data analysis, modeling, validation, deployment, and facilitating adoption by business teams.
• Create intelligent AI-driven agents that automate marketing analytics workflows, such as generating segmentation narratives, campaign insights, reports, and data quality assessments.
• Design and implement Claude Skills, custom tools, and workflow automations to extend AI agent capabilities within defined safety boundaries.
• Develop and apply models for pricing optimization and price elasticity to drive revenue growth, profitability, and market share enhancement.
• Construct customer segmentation and targeting models using unsupervised learning techniques like K-Means, Gaussian Mixture Models, and DBSCAN.
• Build predictive and statistical machine learning models employing Regression, Random Forests, Decision Trees, Support Vector Machines, among others.
• Formulate Bayesian regression and hierarchical Bayesian models using tools such as PyMC or Stan.
• Apply experimental design and causal inference methodologies, including A/B testing, geo-experiments, Difference-in-Differences, Synthetic Control, and Regression Discontinuity for robust business insights.
• Develop constrained, multi-objective optimization algorithms for pricing, advertising budget allocation, and complex business decisions using mathematical optimization libraries.
• Deploy and operationalize models on cloud platforms, particularly AWS SageMaker.
• Utilize model interpretability methods like SHAP to translate analytical outputs into clear business actions.
• Engage with clients and senior management to discern business challenges, present findings, and recommend strategic data-driven solutions.
• Establish and uphold standards for model development, experimentation, documentation, version control, reproducibility, and governance.
• Review and validate models produced by team members, ensuring high statistical and technical quality.
• Identify new opportunities where advanced data analytics can generate tangible business impact.

Qualifications

• Minimum four years of practical experience in data science or related quantitative roles, including leadership or mentoring responsibilities.
• Strong programming capability in Python with expertise in libraries such as pandas, NumPy, and scikit-learn.
• Advanced SQL skills capable of handling complex queries involving joins, window functions, aggregations, and working with large datasets.
• Solid grounding in applied statistics, probability, regression, hypothesis testing, model evaluation, and inference methods.
• Hands-on use of Bayesian modeling, K-Means clustering, Gaussian Mixture Models, DBSCAN, regression techniques, random forests, decision trees, and support vector machines.
• Experience in feature engineering, rigorous model selection, validation, hyperparameter tuning, and assessing model performance.
• Familiarity with model explainability approaches, specifically SHAP or alternatives.
• Practical knowledge in pricing optimization, price elasticity, revenue maximization, or related decision science challenges.
• Exposure to Marketing Mix Modeling (MMM), adstock modeling, saturation analysis, response curve modeling, and optimization of marketing budgets is preferred.
• Proven skills in experimental design and causal inference including A/B testing, geo experiments, Difference-in-Differences, Synthetic Control, and Regression Discontinuity.
• Capability to rigorously evaluate causality, quantify uncertainty, and implement experimental insights into business recommendations.
• Experience deploying machine learning models and conducting experiments on AWS, especially with SageMaker.
• Industry experience in financial services, retail, media, marketing, loyalty programs, payments, or customer analytics is a significant advantage.
• Master’s degree or higher in Data Science, Statistics, Mathematics, Economics, Computer Science, Engineering, or another quantitative discipline is preferred.

Additional Information and Benefits

• Competitive compensation aligned with your expertise, recognizing your contributions fairly.
• Opportunities for rapid professional development supported by mentorship, tools, and programmatic growth experiences.
• Innovation encouraged through collaborative "Idea Tanks" where you can propose and experiment with new concepts.
• Informal "Growth Chats" providing learning occasions with colleagues to enhance skills in a relaxed setting.
• Access to a dedicated Snack Zone to keep energized throughout the workday.
• A culture of recognition featuring regular rewards and acknowledgement programs celebrating achievements.
• Support for continuous professional growth through company-sponsored certifications in AI, Data Science, Cloud, and Analytics.