I engineer real-time computer vision systems that read human motion at machine speed — turning raw video into biomechanical insight for sports analytics, from sub-30ms edge inference to production-grade deep learning pipelines.
A Computer Vision Engineer obsessed with how machines see and understand human motion.
I am a Computer Vision Engineer & AI Specialist based in Islamabad, Pakistan. I design and deploy end-to-end deep learning pipelines — from video preprocessing and dataset annotation to edge and cloud inference — using OpenCV, PyTorch and keypoint detection algorithms to turn raw footage into actionable biomechanical insight.
At ID Sports Ventures, I architect real-time video analytics that track athlete performance during live competition, building lightweight keypoint models that run in under 30 milliseconds on edge devices. I am currently open to global remote and relocation opportunities.
Sub-30ms keypoint detection models for live edge inference on streaming footage.
Multi-camera pose data translated into standardized biomechanical performance reports.
Scalable FastAPI backends, Docker containers and optimized inference for the cloud.
The frameworks, models and infrastructure I use to ship vision systems that actually run fast.
Roles that turned research-grade models into production products.
A selection of systems engineered for speed, accuracy and real-world deployment.
Automated 2D pose-lifting model that evaluates joint angles and limb velocities during complex athletic movements, with synthetic data augmentation for robustness under high-speed motion blur.
Lightweight keypoint detection optimized for edge devices — quantized, TensorRT-accelerated models running on live RTSP streaming footage with minimal latency.
ByteTrack-based MOT system that maintains consistent athlete identities through severe occlusion, powering automated scoring and drill assessment in real time.
I am a Computer Vision Engineer and AI Specialist based in Islamabad, Pakistan, specializing in pose estimation, sports analytics, real-time motion tracking, and deep learning.
I specialize in building real-time deep learning pipelines, sub-30ms pose estimation engines, multi-object tracking (YOLO, ByteTrack), and automated biomechanical motion analysis for sports technology.
I am currently a Computer Vision Engineer at ID Sports Ventures, engineering real-time video analytics for athlete performance tracking. I previously worked as a Software Engineer at Oxmite Digital Ltd.
PyTorch, TensorFlow, OpenCV, YOLO, ByteTrack, ONNX Runtime, TensorRT, FastAPI, Docker, CUDA, C++, and AWS — focused on real-time inference and production deployment.
Email muhammadhassangul01@gmail.com or connect on LinkedIn.
Looking for a Computer Vision Engineer who ships production-grade AI? I'm currently open to full-time roles, contract work and collaborations in sports analytics and edge AI.
