Data Scientist / Data Engineer

This person builds the foundation that everything ML-related will eventually stand on. The pipeline that feeds our models is at least as important as the models themselves, and we want it built right before we bring on anyone to consume it. You'll find the right data sources, transform them, and build the pipeline that moves raw inputs into model-ready datasets.

A concrete example of where you'd start: today our sendable-volume analysis runs deterministic, fairly brute-force SQL to produce recommendations. The goal is to evolve that into a probabilistic, ML-driven pipeline — taking that data, understanding it, transforming it, and propagating it automatically through a medallion (bronze/silver/gold) architecture so that an ML engineer can later consume clean, model-ready datasets.

What you'll do

• Identify and evaluate the data sources we need, and assess the state of the data we already have against where we need it to go.
• Design and build data pipelines and transformations — likely on a medallion architecture — so model-ready data flows automatically as new data lands.
• Work primarily with our transactional and analytical data, including 2D analysis results that already exist in text form. (You won't be parsing raw PDFs or CAD files directly — that's upstream.)
• Lay the groundwork that lets us move specific features from deterministic to probabilistic/ML-driven when the time is right.
• Help us figure out how to approach harder data problems — including 3D data, which behaves very differently from tabular data.

What we're looking for

• U.S. citizenship (required). This role works with sensitive government Controlled Unclassified Information (CUI) and is subject to government contract requirements.
• Strong data engineering and data science fundamentals — building real pipelines, not just analysis in notebooks.
• Experience designing data flows that feed ML training and serving (data sourcing, transformation, feature pipelines).
• The judgment to walk into a messy, early-stage data landscape, assess it, and chart a credible path forward.

Nice to have

• Geospatial or 3D data experience, and familiarity with ML pipelines in that space.
• Experience with medallion / lakehouse architectures.