Associate Data Scientist

Koalafi•Arlington, VA

1d•Onsite

About The Position

At Koalafi, we believe in a world where no one has to put an important purchase on hold. That’s why we’re making it easier for more people to pay for big purchases over time. Retailers across the country rely on us to offer flexible lease-to-own financing to their non-prime consumers, while increasing sales and strengthening customer loyalty. Their 2M+ customers love us because we provide a flexible way for them to make payments and give them an opportunity to improve their credit. Our 200+ Koalafi teammates enjoy inspiring and challenging work that accelerates their careers. Interested in learning more about how we’re transforming the financing experience and joining our team? Koalafi is seeking a Data Scientist with up to 2 years of experience to help develop, deploy, and monitor the machine learning models that sit at the core of our portfolio’s profitability. This role is ideal for someone with a strong quantitative foundation who is eager to learn the full modeling lifecycle: designing predictive models, operationalizing them in production, and helping ensure they continue to perform in a dynamic market. You will be a contributor to Koalafi’s decisioning ecosystem, working on models that influence credit outcomes, fraud mitigation, and the financial performance of the company. Alongside developing your technical skills, you will build the business intuition to translate modeling insights into practical decisions, with mentorship and support from an experienced team. This position reports to the Sr. Manager of Data Science and partners with colleagues across Risk, Fraud, Analytics, and Technology.

Requirements

Up to 2 years of experience (including internships, academic, or personal projects) building and deploying machine learning models, with familiarity with the modeling lifecycle from feature engineering to validation.
Up to 2 years of experience writing Python, including core data science libraries such as pandas, numpy, xgboost, and scikit-learn.
Working knowledge of SQL for querying, transforming, and analyzing datasets.
Understanding of data structures, algorithms, and software engineering principles, with an eagerness to apply them to build robust, scalable solutions.
Bachelor’s degree in a quantitative or STEM field (e.g., Statistics, Mathematics, Computer Science, Engineering), with strong analytical and problem-solving skills.

Nice To Haves

Exposure to credit or fraud risk modeling through coursework, internships, or projects.
Strong analytical foundation, ideally with a Master’s in a quantitative or STEM field, and an understanding of probability, statistics, and predictive modeling algorithms (e.g., Boosting, Random Forests, Decision Trees, Bayesian models).
Exposure to data and compute platforms such as Snowflake and Databricks.
Interest in financial services, or experience in fast-moving, high-growth environments such as startups.
Familiarity with modern ML infrastructure and tooling, including MLOps frameworks (e.g., MLflow, BentoML), CI/CD automation, and model observability and monitoring.
Familiarity with large language models (LLMs) and their deployment.

Responsibilities

Help build, deploy, and maintain production-grade credit and fraud models that support our real-time decisioning platform and portfolio profitability.
Contribute across the MLOps lifecycle: Feature engineering, model training, experiment management production deployment, performance monitoring, and drift detection. (with guidance from senior team members)
Support the development and scaling of end-to-end ML pipelines, helping ensure reliability, reproducibility, and integration with core decisioning services.
Assist in building model monitoring that enables tracing, profiling, explainability, and root-cause analysis for production incidents or model degradation.
Partner with risk and engineering teammates to improve credit policy and strengthen fraud defenses in response to customer behavior and macroeconomic trends.
Contribute to the continuous improvement of existing models by exploring new data sources, techniques, and validation processes.
Communicate model logic and insights clearly, learning to link modeling decisions to business outcomes.