We are looking for a Senior Data Scientistto play a critical role in developing, deploying, and maintaining the intelligent solutions that drive our lending services. This role is built for a practitioner who enjoys full-cycle ownershipfrom architecting data pipelines and credit scorecards to optimizing the decision frameworks that enhance our operational efficiency.
As a senior member of our team, you will bridge the gap between raw data and real-time lending strategies. You will collaborate with cross-functional stakeholders to ensure that our models are not only mathematically sound but also seamlessly integrated into production environments.
Responsibilities:
- Scorecard Development: Build, implement, and monitor credit risk models from raw data to production, specializing in models leveraging alternative data sources such as Telco and Retail.
- Data Engineering & Orchestration: Own the data lifecycle. You will be responsible for sourcing, preparing, and validating datasets using SQL, Python and PySpark, ensuring high-quality inputs for all modeling workstreams.
- Decision Engine Architecture: Translate risk strategies and model outputs into executable logic within the Decision Engine, ensuring seamless real-time processing of lending applications.
- Production MLOps: Maintain and monitor production systems, addressing concept drift and ensuring the continuous delivery of the ML application.
- Strategic Collaboration: Partner with the business and engineering teams to define data requirements and translate quantitative findings into clear, actionable risk strategies.
Requirement:
- Bachelor's or Master's degree in Computer Science, Data Science, Engineering, or a related field.
- 3-5 years of hands-on experience in Data Science or a related quantitative field.
- Expert proficiency in Python and SQL. Advanced experience with PySpark is essential for handling large-scale data engineering and preparation tasks.
- Strong understanding of predictive modeling, feature engineering, and statistical validation. Experience with scorecard development (e.g., WoE, IV, Logistic Regression, Gradient Boosting) is highly beneficial.
- Proven ability to handle raw data and build your own pipelines. You should be comfortable managing the data preparation phase of the modeling lifecycle independently.
- Proficient with Databricks, Google BigQuery, Docker, and version control (Git/Bitbucket).
