Edge AI & TinyML

AI that runs where the data is.

Vision, audio and sensor models on the device — no round trip

We take the models from our AI Labs and make them fit: quantised, pruned and profiled to run on a microcontroller, a Jetson or the NPU in your SoC. The device sees, hears and decides on its own — in milliseconds, on milliwatts, with the data never leaving it.

Let’s manage Open Kanban

Computer vision running on an edge device

01 / What we build

Perception and decisions, on-device.

Vision on the edge

Detection, classification and tracking on cameras — from a Cortex-M to a multi-camera Jetson rig.

Voice & audio

Wake words, keyword spotting, on-device speech and acoustic anomaly detection.

Sensor intelligence

Predictive maintenance, gesture and activity recognition from IMU and industrial sensors.

Model pipeline

Data collection, training, quantisation, on-device evals and OTA delivery as one loop.

02 / Stack

The technology we build with.

Industry-standard, boring in the good way: tools with a future, that the next engineer will know too.

Inference runtimes

TensorFlow Lite / LiteRT
Quantised models on MCUs and mobile SoCs
ONNX Runtime
Portable inference across CPUs, GPUs and NPUs
TensorRT & DeepStream
GPU-accelerated vision pipelines on Jetson
Edge Impulse & TinyML
Rapid model iteration for constrained targets

Target hardware

Cortex-M with CMSIS-NN
Keyword spotting and anomaly detection in kilobytes
NVIDIA Jetson
Multi-camera vision at the edge
Google Coral / Hailo
Dedicated accelerators for low-watt inference
Qualcomm & NXP NPUs
On-SoC acceleration in production devices

Model pipeline

PyTorch
Training, distillation and export
Quantisation & pruning
INT8 / INT4 models that keep their accuracy
Evals on-device
Accuracy, latency and power measured on the target
OTA model delivery
Models shipped and rolled back like firmware

03 / Approach

How we build things that last.

Measured on the target

Latency, memory and current draw are measured on the real device, every model revision.

Milliwatts, not watts

Duty-cycled inference and accelerators chosen for the power budget the product actually has.

Private by design

Raw data stays on the device; only what the product needs leaves it — if anything does.

One pipeline, device to cloud

Data from the fleet feeds training; a better model ships back as an ordinary update.

04 / Standards

Best practices we don’t skip.

We adhere to industry standards and proven methods on every project — they are what makes the estimate hold.

Baseline the task with the simplest model that could work
Quantisation-aware training before post-training tricks
Accuracy evals on real device captures, not the lab set
Latency and power budgets fixed as acceptance criteria
Fallback behaviour defined for low-confidence outputs
Model versioning and rollback through the OTA channel
Drift monitoring from fleet telemetry
Privacy review of every signal that leaves the device

05 / Infrastructure

Where it runs, and how it stays up.

On-device benchmarking rigs (latency, memory, power)
Training pipeline fed by fleet data
OTA model delivery with rollback
Drift and accuracy monitoring in production

Start

Want the model on the device?

Tell us what it has to see, hear or predict — and on what hardware. An engineer writes back with an honest scope and price.

Let’s manage or explore AI Labs

AI that runs where the data is.

Vision, audio and sensor models on the device — no round trip