Telit Cinterion is expanding its manufacturing base by adding operations in the USA.

From the new facility in Bristol, Pennsylvania, starting next month, Telit Cinterion will serve the American and global markets with cellular 4G and 5G IoT modules, and OEM customer products such as routers and gateways.

The 750 square metre facility will house manufacturing, testing and quality assurance. Support functions, including engineering and supply chain, will be supported by the company’s existing offices in Research Triangle Park, North Carolina, and Boca Raton, Florida. The first phase of the initiative is expected to create at least 50 high-value jobs.

The start of US production marks the first phase of Telit Cinterion’s long-term commitment to expanding domestic capabilities. The new operation establishes a foundation for continued investment in US manufacturing, workforce development and supply chain resiliency.

“The Bristol facility represents an important step in strengthening trusted technology supply chains and increasing domestic manufacturing capacity for IoT-connected devices and AI-enabled solutions,” said Paolo Dal Pino, Telit Cinterion CEO. “It onshores our trusted manufacturing capability designed to provide US and global customers with greater traceability, quality assurance, operational resilience and greater supply chain transparency that aligns with new regulations in the USA and western countries.”  

• Telit Cinterion has announced its edge AI SDK and planned AI-enabled cellular module variants. The SDK (www.telit.com/edge-ai-sdk/) runs machine-learning models on a module’s own hardware without the need for an external AI accelerator or companion processor.

Expected before the end of the year, the edge AI SDK incorporates LiteRT, formerly TensorFlow Lite, into the Linux-based firmware of upcoming Telit Cinterion AI-enabled cellular modules. Those module variants will span 4G, 5G RedCap and high-performance 5G.

LiteRT runs the standard .tflite format. Developers train and optimise models in established tools, then load the resulting file onto a Telit Cinterion module without rebuilding for a proprietary environment. A model already running on a PC or a Raspberry Pi transfers directly.

The compact runtime fits on small, low-cost modules unable to host larger AI software stacks. That footprint extends on-module inference to hardware previously limited to connectivity.

Sample applications included in the SDK move a model through the full inference pipeline, acquiring sensor data, pre-processing it, running the model and returning the prediction to the industrial application. System integrators retain control over the final model, application logic and deployment architecture. 

In proof-of-concept testing on image classification and object detection, inference consumed no more than 17% of CPU resources. That margin holds the module below the point where thermal throttling would degrade 4G and 5G performance.

Potential user-developed applications include:

• Predictive maintenance: Analyse vibration or audio data from motors, pumps and bearings to identify anomalies before equipment fails.
• Acoustic monitoring: Recognise alarms, breaking glass and other important sound patterns at remote industrial or infrastructure sites.
• Smart metering: Read existing analogue meters through connected cameras and image classification, with no replacement of installed equipment.  

“Industrial IoT teams should not have to redesign their entire device architecture to add practical AI capabilities,” said Marco Argenton, senior vice president at Telit Cinterion. “By bringing a lightweight AI runtime into the cellular module, we help customers reduce system complexity and accelerate the path from proof of concept to a connected industrial solution that can operate reliably in the field.”

Vishal Batra, vice president of software engineering at Telit Cinterion (www.telit.com), added: “The real engineering challenge isn’t simply running AI at the edge. It’s delivering secure, efficient and reliable intelligence within the constraints of a connected embedded device. Our edge AI SDK enables developers to deploy standard AI models directly on Telit Cinterion modules, accelerating development without compromising the trusted connectivity industrial IoT applications require.”