Field notes
Edge AI, transaction systems and security research, from the engineering team.
Building autonomous systems on NVIDIA Jetson
Sensor fusion, perception, path planning, ISO 26262 functional safety, redundancy, V2X and fleet management on NVIDIA Jetson hardware.
NVIDIA Isaac ROS: GPU-accelerated packages for robotics deployment
Isaac ROS is NVIDIA's toolkit for building robots: pre-built, GPU-accelerated packages for visual SLAM, spatial mapping, object detection and motion planning.
3D reconstruction for robotics on NVIDIA Jetson
Stereo depth, LiDAR processing, visual SLAM, Gaussian Splatting and Isaac ROS on NVIDIA Jetson, with measured frame rates for Orin and AGX Thor.
NVIDIA Jetson security for production deployment
Secure boot and fuse programming, OP-TEE and fTPM, container hardening, LUKS encryption, signed OTA updates and zero-trust access on NVIDIA Jetson.
Custom ERP or packaged ERP: how a mid-sized firm decides
How a mid-sized firm chooses between a packaged and a custom ERP: fit to the process, cost over several years, e-invoicing, and the accounting program it keeps.
Adding AI to the software you already own: what to build and what to buy
When a vendor's built-in AI feature is enough, and when AI belongs inside your own system: data that must stay inside, approval by a named person, and questions that need several systems.
Who owns the code you paid for, and what a handover includes
Paying for software does not make you its owner by itself. What to write into the contract, what a handover includes, and what protects you if the supplier stops trading.
A CRM that briefs the board every morning
What a daily board brief should read and contain, why every figure should open its source record, and what the brief should do when a system could not be read.
Real-time computer vision on NVIDIA Jetson
Detection, segmentation, pose and multi-camera analytics on Jetson Orin, with benchmarks and the TensorRT, DeepStream and VPI settings behind them.
Edge AI inference patterns on NVIDIA Jetson
Triton on Jetson, model ensembles, A/B testing, hot-swapping, federated learning and edge-cloud routing: production patterns for edge AI inference.
Advanced TensorRT optimization on NVIDIA Jetson
Dynamic shapes, IPluginV3 plugins, INT8 calibration, 2:4 sparsity and Nsight profiling for TensorRT inference on NVIDIA Jetson AGX Orin.
Stay Updated
New posts by email when we publish.