Initializing AI Vision Core...
CLASS: DETECTING...
FPS: 60.0
INFERENCE: 12ms
EPOCH: 420

Engineering Intelligent Vision for the Real World

Senior Computer Vision & Deep Learning Engineer with an MSc in IoT & Data Science. Specializing in high-accuracy YOLO pipelines, edge deployment, and production-ready AI systems.

The Intersection of Vision & Scalability

Azeem Aslam

Dedicated to building AI systems that solve real-world challenges. From manufacturing defect detection to medical imaging, I deliver production-ready solutions that combine state-of-the-art models with robust engineering.

[01]

Custom AI Architecture

Fine-tuning SOTA models (YOLOv8, YOLOv9, CLIP) for niche industrial data.

[02]

End-to-End Orchestration

Deploying robust apps with Streamlit, Flask, and cloud-native Docker containers.

Mastery Breakdown

  • • Advanced Object Detection
  • • Medical Imaging & Seg.
  • • MLOps (Docker, CI/CD)
  • • Edge AI & Robotics

Professional Runtime Logs

Senior Computer Vision Engineer

OdyxAI (USA Remote) | 2025 – Present

Leading car damage detection pipelines and high-precision annotation workflows for automotive systems.

AI / Data Scientist

Crime Surveillance Unit (Punjab Govt) | 2025 – Present

Architecting analytics pipelines for large-scale security datasets and automated KPI generation.

Computer Vision Engineer

WSP Global (UK) | 2023 – 2024

Delivered high-impact vision models for infrastructure monitoring and asset management.

Computer Vision Specialist

OmniDent.ai (USA) | 2024

Developed real-time pose and gait estimation models for healthcare monitoring using MediaPipe and open-source frameworks.

Data Analyst

Punjab Safe Cities Authority | 2017 – 2023

Contributed to large-scale video analytics and IoT-based urban safety initiatives.

Education History

MSc IoT with Data Science

Salford University | 2023 – 2024

MS Total Quality Management

Punjab University | 2020 – 2022

BS Information Technology

University of Sargodha | 2012 – 2017

Skill Stack

A showcase of my technical capabilities.

Python (95%)
PyTorch/TF (90%)
YOLO (v8, v9) (92%)
OpenCV (88%)
Scikit-learn (85%)
Pandas (90%)
NumPy (94%)
Streamlit (85%)
Hugging Face (82%)
Docker (80%)
Git & GitHub (90%)
FastAPI (75%)

Selected Deployments

LATEST DEPLOYMENT

Manufacturing Defect Detection

Industrial Streamlit application identifying sub-mm defects in production lines using custom YOLOv8 backbone.

YOLOv8 Streamlit
MEDICAL AI

Brain Tumor Segmentation

Deep learning pipeline for MRI analysis, utilizing YOLOv9 for high-recall tumor localization.

YOLOv9 Medical AI
SECURITY

Real-time Weapon Detection

Surveillance-grade AI system for public safety monitoring with zero-lag inference capabilities.

Surveillance YOLOv8
AUTONOMOUS

Industrial Object Detection

Improved YOLO architecture specifically optimized for small object detection in dense manufacturing environments.

Edge AI Optimization
HEALTHCARE

Pose & Gait Estimation

Validated real-time patient monitoring system using MediaPipe for mobility analysis in clinical settings.

MediaPipe Pose Estimation
ANALYTICS

Pakistan Crime Trends

National-scale data visualization platform for crime distribution and police workload distribution.

Big Data SQL

Technical Insights

Aug 15, 2025

A Deep Dive into YOLOv9 for Real-Time Detection

Exploring the architectural shifts in YOLOv9 and how it impacts inference speed.

Aug 01, 2025

Deploying CV Models with Docker and FastAPI

A comprehensive guide to containerizing vision pipelines for scalable production.

Jul 20, 2025

Data Augmentation Strategies in CV

How to combat small datasets using advanced geometric and pixel-level augmentations.