Lead Data Analytics Engineer

Job Purpose

Responsibilities

• You will collaborate with engineers, data scientists, subject matter experts, and customers in the full-stack implementation of data products for mortgage capital markets applications. You will touch every part of the product development process. You will pitch in on exploratory analysis of our data inputs, help lead data modeling and management for internal platforms, and shape end products for our customers. You will take a substantial role in early prototyping and implementation of these products.
• The principal product focus will be in US mortgage and real estate markets. You should be comfortable wading into messy geospatial datasets and bring some existing expertise on how mortgage and/or residential real estate markets work. You will need to build a deep understanding of our sources’ upstream generation processes to evaluate data quality, accuracy, and feature representations.
• You will help define and maintain derived data layers that support a collection of related analytics products. This roadmap will be built up on a common platform of core data assets and technologies, where the efficient ordering of data acquisition, data integration, and product iteration will be critical to keeping outputs maintainable with a lean team.
• Every member of the team shares in QA and testing responsibilities, across all levels of the data warehouse and analytical workflows. You will identify key failure points in these workflows and think about tests and strategies to mitigate them. You will learn every unique way that a source dataset might mangle a ZIP code (and why it matters for product integrity).
  

Knowledge And Experience

• Strong exploratory data analysis skills in SQL and at least one of R, Python, or JavaScript.
• Familiarity with databases and analytical tools that use SQL as a data manipulation language (especially Google BigQuery).
• Working knowledge of DBT (Data Build Tool) or similar SQL templating systems, as well as DAG orchestration tools like Airflow, preferred.
• A strong interest in the application of AI models, including generative AI/LLMs and novel AI architectures, to real data problems. We use LLMs in data processing pipelines and train/deploy our own AI and machine learning models for product-specific features.
• Experience with projecting, measuring, and controlling cloud computing costs for product workflows is important. Designing products with cost considerations in mind is crucial because of the size and complexity of our product data pipelines.
• Experience analyzing US mortgage and residential real estate data. We care about the combination of subject-matter knowledge and clear understanding of the privacy and security requirements involved.
• Good collaboration with engineering teams across the lifecycle of product ideation, prototyping, and productionizing. Some prior experience as a software/data engineer or machine learning engineer is strongly preferred.
• Comfortable using git version control in a collaborative working environment.
• Building your own ETL pipelines will not be a routine responsibility, but be ready to roll up your sleeves in a pinch. Critical thinking about ETL requirements for time series data and backtesting requirements (what did we know, when, and can we reproduce that state of knowledge?) is an important skill.
• Some prior experience with data visualization and statistical or ML modeling will help you succeed. If you do not have experience, you should be excited to learn this on the job.
• Candidates should have excellent written and verbal communication skills to collaborate effectively with in-person and remote technical colleagues, business stakeholders, and client end-users.