> Markdown version of [/jobs/ext/4649204-risk-data-scientist-hybrid](https://www.wearedevelopers.com/jobs/ext/4649204-risk-data-scientist-hybrid). 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).

---

# Risk Data Scientist | Hybrid

- **Company:** Westside Drive In
- **Location:** United States (Remote available)
- **Experience:** Expert
- **Contract:** Permanent contract
- **Skills:** Algorithm Design, Big Data, Software Quality, Data Cleansing, Extract Transform Load (ETL), Data Mining, Python (Programming Language), Machine Learning, NumPy, Raw Data, Standard Sql, SciPy, Feature Engineering, Model Validation, Pandas, Scikit Learn, Statistics Packages, Xgboost
- **Published:** November 9, 2026
- **Apply:** https://arc.dev/remote-jobs/j/redirect/py055088lb

## About the Role

* Minimum of 5 years of professional experience in Data Science, Predictive Modeling or related quantitative fields;
 * Proven experience in developing Credit Scoring, Behavioral Scoring, Rating or Credit Risk models;
 * Advanced proficiency in Python, including hands-on experience with Pandas, NumPy, Scikit-Learn, SciPy, Statsmodels, XGBoost and/or LightGBM;
 * Strong knowledge of SQL for data extraction, manipulation and analysis;
 * Solid understanding of statistical modeling, Machine Learning algorithms and predictive analytics;
 * Experience working with large datasets, data preprocessing, feature engineering and model validation;
 * Bachelor's or Master's degree in Mathematics, Statistics, Data Science, Physics, Engineering or a related quantitative field;
 * Strong analytical and problem-solving skills, with attention to detail and technical accuracy;
 * Ability to explain complex analytical concepts, modeling assumptions and technical results clearly;
 * High level of autonomy, ownership and accountability, with a results-oriented mindset.

## Description

* Develop, calibrate and validate statistical and Machine Learning models applied to credit risk, including Credit Scoring, Behavioral Scoring and Rating models;
 * Extract, process and analyze large volumes of data to identify risk patterns and support predictive modeling;
 * Design and implement scalable, efficient and modular Python code throughout the entire model lifecycle, from data preparation and ETL to production;
 * Perform quantitative analysis, assess model performance and ensure the robustness and reliability of predictive models;
 * Identify and handle data quality issues, including missing values, outliers and inconsistencies;
 * Explore and implement advanced algorithms, libraries and methodologies to improve model accuracy and efficiency;
 * Document modeling assumptions, technical decisions and analytical results;
 * Ensure high standards of code quality, technical accuracy and model performance.