About the Role
Job Description:
We are seeking a highly skilled, results-driven Data Scientist / Analytics Engineer to join our Data Science Development team within Network Planning. In this role, you will lead the modernization, evolution, and scaling of our geospatial and statistical fiber modeling platforms, specifically our proprietary automated routing, network optimization, and Feeder Distribution Hub (FDH) modeling engines.
You will architect and unify complex network routing engines, scale high-throughput geospatial datasets, optimize cloud database performance, and deliver high-impact spatial analytics that directly guide our national broadband infrastructure strategy.
Key Responsibilities
Design, build, and optimize spatial routing and network planning models across core automated planning platforms and fiber mapping engines.
Drive the convergence of legacy spatial planning scripts into a unified, high-performance network modeling stack.
Execute large-scale FDH and Fiber-to-the-Home (FTTH) remodeling using Dijkstra, Kruskal, or other minimum spanning tree algorithms, leveraging network topology and spatial datasets.
Transition and standardize spatial graph processing and routing engines.
Manage large datasets in spatial data formats (e.g., Shapefiles, GeoJSON).
Integrate advanced spatial datasets (OpenStreetMap, enterprise address databases, master location repositories) into automated ETL pipelines for high-accuracy routing and spatial analysis.
Oversee production relational and columnar databases across cloud environments.
Lead continuous database optimization initiatives, including automating table maintenance, rebuilding high-traffic spatial reference cross-reference tables, and tuning long-running queries to maintain low latency.
Build and manage automated workflow pipelines (e.g., Airflow/Python) to streamline real-time data sharing across engineering, analytics, and AI teams.
Implement self-healing scripts, system telemetry monitoring, and strict role-based access security across the modeling stack.
Architect secure, scalable, and cost-effective data infrastructure across multi-cloud environments (AWS and GCP).
Minimum Qualifications
Education:
Bachelor's or Master's degree in Computer Science, Data Science, Geographic Information Systems (GIS), Operations Research, Software Engineering, or a related quantitative field.
Experience:
5+ years in data engineering, geospatial analytics, or data science roles, with demonstrated leadership in technical delivery.
Core Languages & Frameworks:
Proficiency in Python 3.x, SQL, and microservices/web frameworks (Flask, FastAPI, or Django) is required.
Spatial & GIS Expertise:
Deep experience with spatial analytics tools, spatial SQL, PostGIS, ESRI/ArcGIS frameworks, and open-source mapping platforms (e.g., Overture Maps, QGIS, pg\_tileserv).
Database Systems:
Demonstrated experience with transactional and analytical databases (PostgreSQL, Oracle, Redshift, BigQuery).
Workflow Automation & Cloud:
Hands-on experience with Apache Airflow, Docker, AWS (EC2, RDS), and GCP (BigQuery, Cloud Storage).
Preferred Qualifications
Direct experience in telecommunications network planning, fiber infrastructure deployment (FTTH, FWA), or complex graph/network routing algorithms.
Proven track record of system performance tuning, query optimization, and cost-reduction initiatives across enterprise cloud environments.
Key Competencies
Technical Ownership:
Strong ownership mindset, with a track record of driving complex engineering projects from inception to production.
Collaborative Leadership:
Ability to work cross-functionally with Network Planning, IT, Network Operations, and Executive Analytics teams.
Problem Solving:
Exceptional analytical skills for diagnosing performance bottlenecks in large-scale spatial modeling environments.