// About Me

Dr. Farshid
Pirahansiah

Senior AI Engineer · Computer Vision Researcher
Edge AI Specialist · PhD · Author & Speaker

11+
Years Experience
21
Publications
3
Patents
38%
Inference Cost Cut

// Professional Identity

I build intelligent systems that see, understand, and act — from real-time edge AI on embedded hardware to large-scale MLOps pipelines in the cloud.

With a PhD in Computer Vision and over 11 years bridging research and production, I specialise in taking AI from prototype to deployment — whether that's running embedded deep learning models on a Nvidia, Raspberry Pi, Axelera, Hailo AI chip or scaling medical imaging analysis to tens of thousands of patients daily.

Computer Vision Edge AI Medical Imaging MLOps Embedded Systems 3D Reconstruction IoT Cloud ML

My journey into AI began with a fascination for how machines could be taught to perceive the physical world. During my PhD, I developed fuzzy logic systems for camera calibration and image segmentation — work that led to patents and set the foundation for a career at the intersection of theory and hardware.

Over the years I have worked across academia, enterprise, and deep-tech — from MIMOS (Malaysia's national ICT research centre), where I built patented Intelligent Video Analytics systems, to medical device companies improving diagnostic accuracy through computer vision, to cutting-edge edge AI deployments on Hailo AI and Axelera Metis hardware today.

I speak at workshops and industry events, engage with investors in the computer vision space, and believe strongly that knowledge compounds fastest when shared. My GitHub, publications, and open projects reflect that commitment to the community.

Beyond the code, I am driven by a simple conviction: optimisation is the art of making systems work better without compromising quality — and that principle applies equally to neural networks, camera pipelines, and the teams that build them.

02

Core Expertise

// Vision

Computer Vision & Deep Learning

Real-time object detection, hand landmark estimation, stereo calibration, 3D reconstruction, medical image analysis, and SLAM.

OpenCVPyTorchTensorFlowMediaPipeONNX

// Edge

Edge AI & Embedded Systems

Deploying AI models on resource-constrained hardware — Hailo AI, Axelera Metis, NVIDIA Jetson, Raspberry Pi, and Intel NCS2.

HailoRTGStreamerTFLiteYoctoCUDATinyML

// Cloud

MLOps & Cloud Infrastructure

End-to-end ML pipelines, CI/CD automation, containerised deployment, and real-time monitoring at scale.

AWSDockerKubernetesMLflowAirflowTerraform

// Camera

Multi-Camera Systems

Stereo calibration, depth estimation, 3D scene reconstruction, multi-stream pipeline design, and sensor fusion.

Intel RealSenseOpen3DNumPyMFCamera

// Research

AI Research & Publications

21 peer-reviewed publications and 3 patents spanning image processing, fuzzy logic, OCR, and autonomous vision systems.

MATLABFuzzy LogicBayesian Opt.Active Learning

// Systems

Software Architecture

Full-stack system design, API integration, cross-platform deployment, and technical leadership across distributed teams.

PythonC++LinuxGitCI/CDAgile
21
Peer-Reviewed Publications
3
Granted Patents
11+
Years in AI R&D
03

Selected Projects

2026

Edge AI Pipeline

Real-time embedded deep learning models multi object detection and tracking on sensor fusion and multi camera system on the NVidia, Axelera, and Hailo SoC using GStreamer, HailoRT, and MediaPipe — optimised for embedded Linux deployments via Yocto.

Hailo AIGStreamerYoctoUbuntu
40%latency reduction
Ongoing

Intelligent Video Analytics (IVA)

Patented video analytics platform developed at MIMOS — covering pedestrian density, anomaly detection, licence plate recognition, and real-time event classification.

PythonC++OpenCVMATLABPatent
3patents granted