Data Scientist

Data Scientist - Credit Risk Loan

Key Responsibilities:

• Rapidly prototype tree-based machine learning models (XGBoost, LightGBM, Random Forest) to evaluate new external data sources.
• Retrain existing credit risk models with additional bureau, open banking, telco, or alternative datasets to measure incremental model lift.
• Build new prototype credit models from scratch using internal and external data.
• Perform exploratory data analysis, feature testing, and data value assessment.
• Provide insights on model performance, data quality, and predictive power.
• Work closely with a business analyst and collaborate with a small, distributed team.
• Focus exclusively on early-stage model development (no productionizing or MLOps).

Experience & Skills Required:

• Strong hands-on experience with tree-based classification models (XGBoost, LightGBM, Random Forest, Gradient Boosting).
• Proficiency in Python for data science (Pandas, NumPy, scikit-learn).
• Solid SQL skills for data wrangling and dataset preparation.
• Experience working with cloud environments (AWS, GCP, or Azure).
• Background in credit risk, fraud risk, lending analytics, or financial services modelling.
• Ability to work in fast-paced prototyping environments following an 80/20 approach.
• Strong English communication skills and ability to collaborate with remote team members.

Project Overview:

Our client is building a new function focused on rapidly evaluating external data sources for use in credit and risk modelling. This position is dedicated to early-stage experimentation, fast modelling cycles, and assessing whether new data sources improve predictive performance. Work is fully remote, requires overlap with EST/CST hours, and offers long-term extension potential.

Apply directly or send your profile to d.kasneci@enzotechgroup.com