Embedded AI applications
Deploying vision and inference workloads on edge hardware, from model to production pipeline.
Embedded software consulting
Build a proof of concept, hit a deadline, or simply fill a staffing shortage.
Deploying vision and inference workloads on edge hardware, from model to production pipeline.
Speeding up compute-heavy code with GPU kernels and CPU vector instructions.
Integrating and extending the frameworks that move data between sensors, accelerators, and applications.
Connected devices from the sensor to the cloud: device software, provisioning, and fleet updates.
Independent architecture and code reviews, test strategy, and getting stalled projects shipping.
Automotive, autonomous driving
At Rivian: middleware that coordinates real-time AI and vision workloads across CPUs, GPUs, and specialized accelerators, running in production across tens of thousands of vehicles.
High-voltage asset monitoring
At TerraSense Analytics: leadership of hardware and software development for CRWN, with multi-SoC STM32 devices recording ultrasonic audio, a custom LoRa protocol with cellular transmission, edge AI processing, and a server-side database and GUI.
Defense
At TerraSense Analytics: technical leadership of MIST, with NVIDIA DeepStream and GStreamer pipelines processing multiple video streams with AI at the edge, Cassandra and Kafka for data, and an integrated GUI.
Tell me what you're building and where it's stuck. I'll reply within two business days with whether and how I can help.