Software Engineer – C#/.NET, Applied ML & Data Automation
About the role
In This Role
In this role, you will build and maintain automation tooling that supports industrial telemetry onboarding and data standardization. You will develop C#/.NET-based applications and services that transform device templates and historical tag data into structured configuration outputs used by downstream cloud data pipelines.
A key part of the role involves applied machine learning, including developing and refining classification models that help map telemetry tags to the correct template fields. You will work with historical datasets, improve model accuracy and coverage, validate telemetry data end-to-end, and help reduce manual onboarding effort through automation.
You will also support modernization efforts for legacy systems, troubleshoot production issues, document your work, and collaborate with engineering and data teams to deliver reliable, maintainable solutions.
Responsibilities
- Design, develop, test, and maintain C#/.NET automation tools, including console applications and Worker Services.
- Build tooling that converts Excel-based device templates into structured CSV, configuration, or pipeline-ready outputs.
- Develop and refine applied machine learning models for telemetry tag classification and template-field mapping.
- Perform feature engineering and data preparation using messy historical industrial controls and telemetry datasets.
- Prototype ML or data-processing approaches in Python when appropriate, then help transition production logic into the core C#/.NET stack.
- Validate telemetry data quality and mapping accuracy across cloud-based data pipelines.
- Work with Azure IoT, Event Hub, Kusto/KQL, and related data services to troubleshoot and verify end-to-end data flow.
- Modify, maintain, and enhance existing databases, database structures, and legacy systems as needed.
- Partner with stakeholders to gather requirements, estimate scope, and deliver solutions from development through testing and release.
- Identify opportunities to reduce manual processes, improve onboarding efficiency.