Parsa Rezaei
Services

Embedded & Edge AI

Models that actually run on the hardware you are shipping.

Most machine learning works fine on a workstation and falls apart on a battery-powered board. I take models the rest of the way: choosing an architecture that fits the silicon, quantising it until it meets the latency and power budget, and building the inference pipeline around it so it survives contact with real hardware.

Engagements

What you can hire me for

  • 01Get an existing model running on a target board within a power and latency budget
  • 02Architecture and quantisation review before you commit to hardware
  • 03Build an on-device inference pipeline with sensor input and real-time output
  • 04Stand up orchestration and OTA updates across a fleet of edge devices
  • 05Second opinion on whether an edge deployment is feasible at all
Evidence · 4

Where this shows up