About DigitalStarr Technologies

DigitalStarr Technologies LLC is an information technology and digital transformation company specializing in Artificial Intelligence, Data Analytics, Cloud Computing, GIS, and enterprise digital solutions. The company partners with federal, state, and local government agencies and commercial organizations to design, implement, and support innovative technology solutions that deliver measurable business outcomes.

Position summary

The successful candidate will apply statistical methodologies, machine learning techniques, and data engineering practices to transform large and complex datasets into actionable insights that improve property acquisition, surplus inventory management, land valuation, geospatial analysis, and business process optimization.

Essential duties and responsibilities

• Design and implement scalable data collection and structuring workflows using REST APIs, Apache Spark, and Microsoft Azure Data Factory.

• Acquire and integrate multi-source datasets containing millions of records to support advanced analytics and machine learning applications.

• Perform advanced data wrangling, cleansing, normalization, aggregation, transformation, and feature engineering across heterogeneous datasets.

• Develop predictive frameworks using multivariate regression, distribution modeling, hypothesis testing, anomaly detection, gradient boosting, classification, and other machine learning techniques.

• Perform model optimization, hyperparameter tuning, and validation using metrics such as accuracy, precision, and recall.

• Develop automated validation procedures to detect inconsistencies, duplicates, computational errors, and improve reproducibility of analytical outputs.

• Create dashboards and analytical visualizations using Microsoft Power BI and Python, and communicate findings to technical and non-technical stakeholders.

• Analyze Right of Way, property acquisition, easement, relocation, land management, surplus property, valuation, asset utilization, and GIS datasets to support public-sector property management initiatives.