> Markdown version of [/jobs/ext/4662685-data-scientist-collection](https://www.wearedevelopers.com/jobs/ext/4662685-data-scientist-collection). Every page supports `.md` or `Accept: text/markdown`. Links point to the HTML versions so they work for humans too. Agent guide: [/agents.md](https://www.wearedevelopers.com/agents.md). --- # Data Scientist - Collection - **Company:** VITALUS HEALTH, LLC - **Location:** Sunnyvale, CA, United States (Remote available) - **Contract:** Permanent contract - **Skills:** A/B Testing, Artificial Intelligence, Amazon Web Services, BigQuery, Python (Programming Language), Machine Learning, Cloud Services, SQL Databases, Large Language Models, Git, Pandas, Scikit Learn, Xgboost, Software Version Control - **Published:** November 10, 2026 - **Apply:** https://arc.dev/remote-jobs/j/redirect/py9srefuig ## About the Role * Hands-on experience with collection, credit, or credit card portfolios. * Strong analytical mindset: you break down messy problems with data and reach clear, actionable conclusions. * Experience building statistical and machine learning models that drive business decisions. * Fluency in Python and SQL, with proficiency in libraries such as pandas, scikit-learn, XGBoost/LightGBM, or similar. Nice to Have * Experience with experimentation (A/B tests, champion/challenger strategies) and causal inference. * Experience deploying and monitoring models in production. * Familiarity with cloud data platforms (GCP/BigQuery or AWS) and version control (Git). * Experience with LLMs and Agents. * Builder and proactive mindset: you take ownership and create solutions, not just reports. * As a member of a fully remote and distributed team, you are expected to complete tasks autonomously, being highly collaborative and self-driven. * Ability to communicate effectively in both English and Portuguese. ## Description * Own credit card collection intelligence. Design strategies, analyses, and models built specifically for our credit card portfolio. * Build decision models. Develop and improve models such as propensity to pay, risk segmentation, and treatment and channel optimization to drive collection actions. * Turn data into strategy. Analyze collection performance, design experiments, and translate findings into concrete changes in policies and flows. * Ship to production. Partner with engineering and operations to put models and rules into production and monitor their performance over time. * Expand the scope. Collaborate with the team's lending modeling work and take on other collection fronts as the business grows. * Use AI as a practical accelerator for analysis, coding, and operations, not only as a chat assistant.