ML Data Engineer - Mortgage Credit Risk

Anza MI is a fintech startup using technology and analytics to drive growth & innovation within the US mortgage market.

About the role

As a ML Data Engineer embedded in Anza MI's Data Science practice, you will be a key enabler of our efforts to automate key business processes. The team uses a cloud-native technology stack to analyze mortgage-related data, train a suite of predictive models, and automate operational processes. Your primary responsibility will be to use document processing solutions to automate and streamline our Quality Control and Independent Validation operations.


You will have the opportunity to develop across these skills dimensions through mentorship and your portfolio of work. In addition to working within the Data Science function, you will also be responsible for learning and adhering to the engineering best practices established by the wider Technology organization to ensure alignment and consistency. A ML Data Engineer will work autonomously and in partnership with more senior members of the team as well as work closely with business partners.


What you'll do

• Data Pipeline and Integration: Implement and maintain scalable and reliable ETL/ELT data pipelines to support analytics and modeling workflows.
• Infrastructure and Tools: Build and maintain critical data infrastructure on Databricks.

• Document Processing: Help build a greenfield automated system that uses AI/ML to extract and analyze data from large mortgage document packets.

• Team Collaboration: Work with the Senior Data Engineer, facilitate the Data Science team's goals, and follow engineering practices of the Technology team.

• Continuous Learning: Improve engineering skills as well as knowledge of our market and business (mortgage and housing finance).

Qualifications

Minimum Education

• Bachelor's degree in computer science, Engineering, Data Science, or related fields.

Minimum Years of Experience

• 0 to 2 years

Minimum Skills

• Proficiency in Python and SQL, a solid understanding of cloud platforms (e.g. AWS, Azure), orchestration tools (e.g. Airflow, dbt) and data modeling.

Preferred Education

• Master's degree in computer science, engineering, data science, or related fields.

Preferred Years of Experience

• 1 to 2 Years

Preferred Skills

• Proficiency in Apache Spark, software engineering and CI/CD practices. Experience with data analysis in a business setting.