Quantitative Data Engineer - Fixed Income and Mortgages

Selby Jennings; New York (NY); On-site; USD 150,000 - 230,000; Full time

Job summary

Selby Jennings is seeking a Quantitative Data Engineer to partner with Quantitative Research, owning end-to-end data workflows for loan-level and structured credit modeling. This hands-on role develops data acquisition, feature generation, model inputs, and production-ready datasets used across analytics and risk teams.

You will design large-scale pipelines for credit and mortgage analytics, build loan-level feature workflows, and productionize research outputs, collaborating with Research,

Qualifications

• Strong Python development with production-quality code and testing.
• Deep experience with Spark/PySpark and performance tuning.
• Advanced SQL across data warehouses (Snowflake/Redshift/BigQuery).
• Experience building analytics datasets and ML feature pipelines.
• Knowledge of reproducible pipelines, experiment tracking, and version control.
• Experience in Git, CI/CD, and collaborative engineering environments.

Responsibilities

• Design and maintain large-scale data pipelines supporting credit, mortgage, and structured product analytics.
• Build and optimize loan-level feature engineering workflows and model input datasets.
• Develop reproducible data processing frameworks that support research, validation, and production deployment.
• Partner with quantitative researchers to implement new features, validate methodologies, and improve model performance.
• Work with engineering teams to productionize research outputs and improve platform scalability and reliability.
• Support ad hoc quantitative analysis and investigation of portfolio, collateral, and performance datasets.

Skills

Python

Spark

SQL

Feature engineering

Data pipelines

CI/CD

Team collaboration

Education

Bachelor's / Master's / PhD in a quantitative field

Tools

Snowflake

Redshift

BigQuery

Delta Lake

Databricks

Polars

Pandas

scikit-learn

Job description

Quantitative Data Engineer - Fixed Income and Mortgages

The Quantitative Data Engineer partners closely with Quantitative Research and is responsible for the end-to-end data workflow that supports loan-level and structured credit modeling. This role owns data acquisition, feature generation, model inputs, and production-ready datasets used across quantitative investment and risk analytics. It is a hands-on engineering position for someone who wants to work directly alongside researchers and contribute to the development, deployment, and improvement of data-driven models.

The role collaborates with Research, Engineering, and Investment teams to build scalable analytics and machine learning infrastructure that supports investment decision-making.

Core Responsibilities

• Design and maintain large-scale data pipelines supporting credit, mortgage, and structured product analytics.
• Build and optimize loan-level feature engineering workflows and model input datasets.
• Develop reproducible data processing frameworks that support research, validation, and production deployment.
• Partner with quantitative researchers to implement new features, validate methodologies, and improve model performance.
• Work with engineering teams to productionize research outputs and improve platform scalability and reliability.
• Support ad hoc quantitative analysis and investigation of portfolio, collateral, and performance datasets.

Required Qualifications

• Strong Python development experience, including production-quality code, testing, packaging, and code review practices.
• Deep experience with distributed data processing using Spark and PySpark, including optimization of joins, partitioning, caching, skew management, and execution performance.
• Advanced SQL skills and experience querying large columnar data warehouses such as Snowflake, Redshift, BigQuery, Vertica, or similar platforms.
• Experience building analytical datasets and feature engineering workflows for machine learning, statistical modeling, or quantitative research.
• Strong understanding of reproducible data pipelines, experiment tracking, artifact management, and version-controlled development.
• Experience working in shared engineering environments utilizing Git, automated testing, and CI/CD processes.
• Ability to work directly with quantitative researchers and translate research requirements into scalable engineering solutions.

Preferred Qualifications

• Experience working with loan-level, mortgage, consumer credit, or structured finance datasets.
• Exposure to prepayment, default, transition, or loss modeling in credit or securitized products.
• Familiarity with market and reference data providers, securitization cash flows, collateral reporting, or structured product analytics.
• Experience with Databricks, Delta Lake, workflow orchestration tools, and modern cloud-based analytics platforms.
• Exposure to model deployment, scoring frameworks, experiment tracking, or machine learning operations.
• Experience with high-performance analytics tools such as Polars, DuckDB, Pandas, and scikit-learn.
• Familiarity with workflow scheduling, data quality monitoring, and pipeline validation.
• Comfortable using AI-assisted development tools to accelerate coding, refactoring, testing, and codebase navigation.
• Knowledge of cloud infrastructure, object storage, access controls, and cost-efficient data architecture.

Education

• Bachelor's, Master's, or PhD in Computer Science, Data Science, Statistics, Financial Engineering, Mathematics, Economics, Physics, Engineering, or a related quantitative discipline.
• Candidates from adjacent industries are welcome, particularly those with strong distributed computing, data engineering, and machine learning experience.