AI-powered predictive maintenance for mining equipment using sensor fusion
Razor Labs builds sensor-fusion predictive maintenance systems for mining operations, using Python, BigQuery, and PostgreSQL to ingest and analyze multi-modal sensor data (vibration, temperature, pressure, oil, video) and forecast equipment failures before they occur. The engineering-heavy hiring focus—6 of 11 open roles—paired with active projects spanning edge device automation, backend AI systems, and sensor integration, signals investment in scaling both the data pipeline and field deployment infrastructure. Pain points around device connectivity and data transmission suggest the core technical challenge is reliable edge-to-cloud data flow in remote mining environments.
Razor Labs is a publicly traded mining-technology company founded in 2016, headquartered in Sydney with offices in Perth and Tel Aviv. The company develops predictive maintenance platforms that combine machine learning with multi-sensor data streams to predict equipment failures, reduce unplanned downtime, and improve safety in mining operations. Solutions are deployed at sites across Western Australia and South Africa. The product stack centers on condition monitoring and root-cause analysis, enabling mining operators to optimize equipment reliability and avoid costly production interruptions.
Python, BigQuery, PostgreSQL, Docker, Terraform, Ansible, Linux, and Figma for design. The stack emphasizes cloud data warehousing and infrastructure-as-code for scalable deployments.
Active projects include edge device automation, backend AI system development, sensor-based condition monitoring deployments, and integration of sensor installation with fixed mining assets. Edge infrastructure and deployment streamlining are core development areas.
Other companies in the same industry, closest in size