Junior Data Scientist

Role Overview

This position sits within the data team and focuses on turning messy operational, customer, and lending data into clear information that teams can act on. Day to day, the junior data scientist will query databases, investigate portfolio and borrower trends, and prepare reporting that supports credit, product, operations, and finance decisions. The role also provides a path into applied machine learning and credit scoring work, with senior colleagues providing direction and review.

Key Responsibilities

• Use SQL to pull, clean, reshape, and examine data from multiple sources so analyses are accurate and repeatable.
• Build and refresh routine weekly and monthly reports on business performance and lending portfolios for internal and external audiences.
• Explore datasets to surface patterns, shifts, outliers, and data quality issues that need attention.
• Answer analysis requests from Credit, Product, Operations, and Finance teams, translating their questions into data work.
• Study repayment behavior, customer segments, and lending indicators such as disbursements, repayment rates, PAR, DPD, collections, and portfolio health.
• Assist with tracking credit risk signals and monitoring how scorecards or models perform over time.
• Partner with senior data scientists to assemble datasets, engineer features, run validation tests, and evaluate classification or credit-scoring prototypes.
• Keep documentation current for metrics, queries, ETL logic, dashboards, and shared SQL references so others can reuse and trust the work.

Requirements & Qualifications

• Bachelor’s degree in statistics, mathematics, economics, computer science, engineering, or another quantitative field; coursework in probability, regression, or data analysis is strongly relevant.
• Around 1–2 years of hands-on experience in a data analyst, data science, or analytics role, including internships or academic projects with real datasets.
• Solid SQL ability: joins, aggregations, subqueries, window functions, and cleaning messy tables.
• Working knowledge of Python or R for analysis, with libraries such as pandas, NumPy, scikit-learn, or similar.
• Familiarity with exploratory analysis, descriptive statistics, hypothesis testing, and basic predictive modeling concepts.
• Comfort with spreadsheets and data visualization tools for reporting.
• Ability to explain findings clearly to non-technical partners and document work so it can be reproduced.
• Exposure to credit, lending, fintech, or portfolio analytics is helpful but not required.
• Attention to detail and a habit of checking numbers before they reach decision-makers.

Why Join

• Work on practical problems across customer behavior, lending performance, transactions, credit risk, and operations rather than isolated exercises.
• Gain guided exposure to machine learning and credit-scoring projects while contributing to real model evaluation work.
• Collaborate with Credit, Product, Operations, and Finance teams, seeing how data informs decisions across the business.
• Build a strong foundation in SQL, reporting, documentation, and analytical QA practices that are valuable for a data science career.
• Join a team that values learning, shared knowledge, and reproducible analysis.