I'm a full-stack data scientist with a background in ML research and data engineering, known for turning complex problems into high-impact, production-ready systems. I specialize in owning the full lifecycle—from early exploratory analysis and prototyping to deploying scalable, maintainable ML pipelines in production environments.
My work spans multiple domains:
- Geospatial & Remote Sensing (NASA): Terrain analysis, flood risk modeling, and spatial feature engineering
- Energy Forecasting (DOE): Probabilistic time-series modeling and demand simulation
- Healthcare & Location Intelligence (CSL): Site selection models for medical centers, using spatial and demographic features
- Startup Ops & Growth (Booster): Simulation tools, pricing optimization, and causal modeling for business decisions
I’m deeply fluent in both modeling and infrastructure:
- Production ML (regression, classification, clustering, forecasting, Bayesian methods)
- End-to-end pipelines with ETL, Reverse ETL, and model observability
- Large-scale computing with Apache Spark and Databricks
- Tools: Python, SQL, Spark, dbt, Airflow, Databricks, PyTorch, scikit-learn, QGIS, AWS
I’m particularly excited by opportunities at the intersection of AI, geospatial, infrastructure, and decision-making—where tight feedback loops between models, data systems, and human insight can unlock massive value.
- Research meets execution
- Business needs are at the center of the project
- Engineers and scientists collaborate
- There's room to own, ship, and scale ideas
Let’s connect:
📫 Email: cjustadsandberg@gmail.com
🔗 LinkedIn: linkedin.com/in/cadejs