Three pillars, one engineer.
Intelligence without the cloud
Model optimization & compression, on-device inference pipelines, edge MLOps — research to deployed hardware.
Detection from any sensor
Acoustic, vibration, vision, and EO/IR analytics with self-supervised, low-label pipelines.
Robots that see; sites you can revisit
Drone & quadruped autonomy, inspection workflows, LiDAR-to-digital-twin pipelines.
Where the work happens
Latest from the R&D log
Quantizing a vibration-anomaly model for a $60 edge board
INT8 on a Cortex-M55 without losing the tail of the distribution.
What 10,000 synthetic spectrograms taught us about input design
A clean-room study on representation choices for condition monitoring.
LiDAR mapping a rail siding with a sub-250g drone
What a featherweight platform can — and cannot — resolve.
The engineer who scopes your problem is the engineer who ships your solution. No account manager, no hand-off, no junior bench.
Have a sensor, a site, or a fleet that should be smarter?
We take on a limited number of engagements per quarter. If your problem involves edge constraints, unusual sensors, or no labeled data — that's our specialty.