← В ленту
Регистрация: 11.09.2026

Abdul Rehman

Специализация: Computer Vision Engineer
I’m a Computer Vision Engineer with around 1.5 years of experience in applied AI and machine learning. Most recently, I worked at Motive on production perception systems for driver safety, including improving object detection models and analyzing real-world failure cases. I’ve also worked on computer vision projects involving YOLO, segmentation, video analytics, and model deployment using PyTorch, OpenCV, Docker, and AWS. I hold a BS in Artificial Intelligence from FAST-NUCES with Magna Cum Laude honors.
Computer Vision PyTorch Python Tensorflow AI C++ AWS scikit-learn Git Machine Learning Docker CI/CD methodologies pandas OpenCV SQL Software Development GitHub Linux JSON
I’m a Computer Vision Engineer with around 1.5 years of experience in applied AI and machine learning. Most recently, I worked at Motive on production perception systems for driver safety, including improving object detection models and analyzing real-world failure cases. I’ve also worked on computer vision projects involving YOLO, segmentation, video analytics, and model deployment using PyTorch, OpenCV, Docker, and AWS. I hold a BS in Artificial Intelligence from FAST-NUCES with Magna Cum Laude honors.
Computer Vision PyTorch Python Tensorflow AI C++ AWS scikit-learn Git Machine Learning Docker CI/CD methodologies pandas OpenCV SQL Software Development GitHub Linux JSON

Портфолио

GlassFill

• Built a YOLOv8 segmentation pipeline to detect glasses and estimate liquid levels using PyTorch, Ultralytics, OpenCV, Flask, and NumPy.

MVision Agent

• Built an agentic video understanding system for automated driving-event validation using multiple vision models and tool-based reasoning. • Orchestrated tools including SAM3, YOLO, Grounded DINO, pose estimation, gaze estimation, depth estimation, and lane detection, with AWS EC2, Bedrock, Boto3, Docker, and GitHub Actions.

EOS

• Built a real-time on-device image classification application using MobileNet, TensorFlow.js, React Native, and Expo.

Скиллы

Python
PyTorch
TensorFlow
YOLO
OpenCV
Computer Vision
NumPy
Pandas
AWS
Docker
C++
C
JavaScript
SQL
Hugging Face
Ultralytics
SAM3
Grounded DINO
Bedrock
Boto3
Flask
React
React Native
Node.js
Firebase
Streamlit
Git
GitHub Actions
scikit-learn

Опыт работы

Software Engineer - ML, Perception
09.2025 - 08.2026 |Motive
Python, OpenCV, NumPy, Pandas, YOLO, C, SQL, AWS
● Debugged and aligned the edge implementation of Forward Collision Warning (FCW) with its cloud counterpart, improving detection precision by 5%. ● Improved speed-sign detection precision by 7.5% by identifying and addressing model failure cases across real-world driving scenarios. ● Worked on production driver-safety perception systems, focusing on debugging, failure analysis, and improving detection performance.
Computer Vision Engineer
01.2024 - 03.2024 |AIO
Python, YOLO, OpenCV, Computer Vision
● Developed real-time computer vision solutions to automate operational tasks in the restaurant industry. ● Customized and deployed YOLO-based object detection models for industry-specific use cases.
Research Assistant
06.2023 - 01.2024 |AIM Lab
Python, Hugging Face, Whisper, Tortoise, VITS, NLP
● Researched XAI, sentiment analysis, and language-model fine-tuning using Hugging Face. ● Developed speech technologies using Whisper, Tortoise, and VITS; co-authored a published TTS dataset paper.

Образование

Artificial Intelligence (Бакалавр)
2021 - 2025
FAST NUCES

Языки

АнглийскийСреднийУрдуРодной