About

We are building a groundbreaking climate-tech platform, "Zero Home Score," to create the highest-fidelity digital twin of the electrical grid, starting at the residential level. We are seeking an elite full-stack engineer to build the initial MVP from the ground up. This MVP will ingest geospatial data (OpenStreetMap), property data, and large-scale energy datasets (DOE's ComStock/ResStock, ERCOT load data, AMI data) to train a sophisticated model that predicts the energy profile and provides a "Zero Score" for every home in a target market. This is a data-intensive application requiring a strong foundation in backend development, data engineering, and a good understanding of how to serve machine learning model outputs efficiently. Key Responsibilities: Architect and build a robust, scalable backend using Python and FastAPI. Design and implement a PostgreSQL database schema with PostGIS for storing and querying geospatial and property data. Develop a data ingestion and processing pipeline using tools like Airflow or Dagster to handle diverse datasets (GeoJSON, CSV, Parquet). Integrate a machine learning model (initially a pre-trained surrogate model) into the backend to generate and serve predictions. Build a responsive, map-centric frontend application using React/Next.js and Mapbox GL JS. Deploy the entire application stack to a cloud environment (AWS or GCP) using Docker. Must-Have Technical Skills: Expert in Python: Deep experience with modern Python (3.9+), including frameworks like FastAPI or Django. Strong Frontend Skills: Proficiency in React (with hooks) and ideally Next.js. Experience with a mapping library like Mapbox GL JS or Leaflet is essential. Database Expertise: Deep knowledge of PostgreSQL and specifically the PostGIS extension for geospatial queries. Data Engineering: Demonstrable experience building data pipelines. Familiarity with an orchestration tool like Apache Airflow, Dagster, or Prefect. DevOps & Cloud: Experience with Docker and deploying applications to AWS (S3, RDS, ECS) or GCP (Cloud Storage, Cloud SQL, Cloud Run). API Design: Proven ability to design and build clean, efficient REST APIs. Great-to-Have (Bonus) Skills: Experience with machine learning libraries (Scikit-learn, XGBoost, PyTorch). Experience with the scientific Python stack (Pandas, GeoPandas, NumPy). Direct experience with energy modeling, utility data (like Green Button), or datasets like ResStock/ComStock. Familiarity with data transformation tools like DBT.