Lead Data Scientist - Growth & Marketing Models

FairSquare•San Diego, CA

32d•$150,000 - $170,000•Hybrid

About The Position

This is a senior/lead level position for a Lead Data Scientist focused on Growth & Marketing Models within a lean, AI-leveraged team at a FinTech lender. The role involves building predictive models and analytics that influence targeting, offer decisions, approvals, and marketing spend. The work directly impacts conversion, credit performance, customer economics, and profitable growth, with models shipping into production and being measured against these outcomes. The team utilizes AI tools like Claude and ChatGPT for analysis, coding, and drafting, emphasizing a verification-first approach. The core focus is customer acquisition modeling for small-business lending, including direct mail and digital targeting, prescreen campaigns, and funnel economics. This is a high-ownership, hands-on role where the individual will lead projects from business question to deployment, monitor results, and mentor other data scientists.

Requirements

Master's degree or higher in statistics, mathematics, computer science, engineering, operations research, economics, or another quantitative discipline — or equivalent hands-on experience shipping production models.
5+ years of relevant data science or machine learning experience, or an equivalent combination of education and experience.
Strong programming skills in Python or R, plus proficiency in SQL and relational databases.
Demonstrated experience with supervised and unsupervised machine learning, statistical analysis, model validation, feature engineering, and experimental design.
Experience building, deploying, monitoring, and maintaining predictive or recommendation models in a live environment.
Strong programming practices, including version control (for example, Git), reproducible analysis, testing, and documentation.
Experience leading end-to-end data science projects, coordinating stakeholders independently, and mentoring other data scientists.
Strong written and verbal communication across technical and non-technical audiences.

Nice To Haves

Growth data science, marketing analytics, customer acquisition, targeting, response modeling, propensity modeling, lead scoring, segmentation, recommendation systems, or personalization.
Direct mail, performance marketing, digital acquisition, cross-sell, retention, customer lifetime value, marketing attribution, or offer optimization.
A/B testing, causal inference, uplift modeling, incrementality measurement, or optimization under business constraints.
FinTech, consumer lending, credit risk, underwriting, pricing, AWS, cloud technology, or production machine learning / MLOps.

Responsibilities

Build targeting, response, propensity, and conversion models for direct mail, digital acquisition, and other growth channels.
Develop customer segmentation, lookalike, lead-scoring, recommendation, and personalization models.
Optimize campaigns, offers, channels, and budgets informed by customer lifetime value, acquisition cost, expected credit performance, and unit economics.
Conduct experimentation and incrementality measurement, including A/B testing, causal inference, and uplift modeling.
Implement and monitor production models for performance, drift, calibration, data quality, and retraining.
Partner with leaders across marketing, credit risk, sales, product, and engineering to translate commercial problems into analytical questions and success criteria.
Own projects end-to-end: data discovery, preprocessing, feature engineering, model development, validation, deployment, monitoring, and iteration.
Work with structured and unstructured data from disparate sources, reconciling conflicting numbers, surfacing data gaps, and driving issues to resolution.
Build and evaluate supervised and unsupervised machine learning models using sound statistical methods, appropriate benchmarks, and transparent assumptions.
Design experiments to distinguish correlation from causation and translate model lift into financial and customer outcomes.
Collaborate with engineering and analytics partners to move models into production workflows, investigate performance changes, and recalibrate, retrain, or replace models.
Communicate recommendations, tradeoffs, uncertainty, limitations, and expected business impact clearly to technical and non-technical decision-makers.
Use AI tools to accelerate analysis, coding, documentation, and communication, while independently verifying logic, calculations, and source data.
Mentor other data scientists, raise modeling and coding standards, and contribute to the evolution of the analytics platform and team practices.