Parsa.Rezaei
Available for new consulting engagements

Engineering for hardware that has to work outside the lab

Embedded systems · Autonomous vehicles · Imaging · FPGA

I am a computer engineer working across embedded systems, autonomous vehicles, imaging and FPGA design. I take on the parts of a programme that sit between disciplines, where the model meets the power budget, where the flight stack meets the airframe, where the sensor meets the test data, and get them working on real hardware.

What I do

4 practice areas
Models that actually run on the hardware you are shipping.

Embedded & Edge AI

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.

View engagements →
Airframe to autonomy, including the parts nobody wants to own.

UAV & Robotics Systems

Whole-vehicle work rather than one slice of it: structures, propulsion, avionics, telemetry and autonomous behaviour, plus the fabrication to actually build the thing. I have taken vehicles from a requirement to a flying, tested prototype across electric, turbine and underwater propulsion.

View engagements →
Characterise it, test it, and prove the numbers.

Imaging & Sensor Systems

Image sensor and detector work: characterisation, bench bring-up, and the data infrastructure that turns raw test output into a decision. This is my day-to-day professional practice rather than research work, and it covers the unglamorous middle of a sensor programme where most schedule risk actually lives.

View engagements →
Custom logic where a CPU will not do.

FPGA & Reconfigurable Computing

FPGA design and hardware/software co-design for cases where timing, throughput or determinism rule out a general-purpose processor. Includes partial reconfiguration, where the fabric changes function at runtime rather than being fixed at build time.

View engagements →

Working together

Most of my work sits at a boundary: a model that has to fit a power budget, a flight stack that has to match an airframe, a sensor whose numbers have to survive production. Those handoffs are where schedules slip, and they are usually nobody specific's job.

If you have a problem shaped like that, tell me what you are trying to build and what is currently in the way.