Senior Data Scientist

One Park Financial•Salt Lake City, UT

About The Position

One Park Financial (OPF) is seeking a seasoned Senior Data Scientist to join their Analytics team. This role is crucial for driving core business transformation by building and testing models and proposals related to pricing, approval, and growth. The successful candidate will own production systems end-to-end, operating and evolving the company's proprietary risk-based pricing engine and real-time offer decisioning application. This position involves close collaboration with business stakeholders to understand problems and implement AI/ML solutions, partnering with DevOps, Product, and Engineering to move models from notebooks to production. A key responsibility will be leading A/B testing initiatives and designing experiments to prove success. The role requires performing EDA, identifying modeling opportunities, feature engineering, ETL, implementing and monitoring models, and highlighting opportunities for change. As an AI-forward company, OPF expects data scientists to leverage modern AI and LLM tooling for faster and sharper analysis, modeling, and experimentation.

Requirements

4-7 years of experience in Data Science and the Financial Industry, preferably in Credit or Lending.
Master's degree in mathematics, statistics, computer science, or data science.
Experience in transforming existing processes with AI/ML-based approaches.
Proficiency in data manipulation.
Excellent SQL and Python skills for data wrangling and ETL.
Hands-on AWS / cloud experience deploying and operating production ML services (compute, storage, IAM, containerized deployment).
Experience building or maintaining production applications and services, not just models in notebooks. You should be comfortable owning software in production.
Experience with dashboard tools such as PowerBI or other visualization tools.
Experience building credit or risk models for Financial Services, Lending, or Insurance.
Experience in validating models to identify ongoing improvements.
Rock Solid data science skillset: Exploratory Data Analysis, Feature Engineering, Fitting, Tuning, and Comparing models, and managing the model Lifecycle.
Experience with statistical modeling and data analysis using programming languages such as Python.
Experience in ML engineering, cloud-based deployment, and machine learning model lifecycle management.

Nice To Haves

Knowledge of best practices for financial and lending models (model risk management, model governance, and fair-lending considerations) is a big plus.
Comfort using modern AI and LLM tools to make your own analysis and modeling more efficient (a plus).
Experience with dbt (major plus).

Responsibilities

Utilize advanced statistical and machine learning techniques to analyze large datasets and build new AI/ML models.
Develop and pressure-test pricing and credit proposals end to end, with the statistical and analytical rigor to prove they will work before they ship. These won't always be models; sometimes the answer is a well-tested policy change.
Conduct exploratory data analysis, feature engineering, and data preprocessing to solve business problems.
Own, operate, and enhance our proprietary risk-based pricing engine (a production Python application), including its models, business logic, deployment, and monitoring.
Facilitate the deployment and monitoring of models for real-time and batch processing.
Own strong model governance: clear documentation and versioning, ongoing monitoring for drift and degradation, regular validation, and a defensible audit trail across the model lifecycle.
Partner with DevOps, Product, and Engineering teams to ship models and features to production, owning the rollout from staging to production, including CI/CD, monitoring, and rollback.
Perform model evaluation and validation on a regular basis to ensure robust performance.
Engineer A/B tests with scientific rigor. Gather test data and validate results to present to business stakeholders.
Use modern AI and LLM tooling to speed up your own work, from EDA and feature engineering to model prototyping, documentation, and testing.
Champion creative uses of existing data to solve business problems with intellectual curiosity.
Produce statistical and data analysis visuals (charts, infographics) to communicate findings clearly and effectively to a non-technical audience.
Collaborate with team members, product managers, and business stakeholders to identify opportunities for new and innovative AI/ML solutions.
Analysis areas could include Onboarding Credit, Ongoing Credit, Marketing segmentation, Voice-based analysis, Text mining, Sentiment analysis, Risk quantification, and Risk-based pricing.