Senior Computer Vision Engineer

Ahdus technology; Islamabad; On-site; PKR 2,400,000 - 4,800,000; Full time

Job summary

Ahdus technology in Islamabad invites a Senior Computer Vision Engineer to lead design and deployment of intelligent vision-based systems, tackling image and video analysis, object detection, tracking, and 3D vision projects using cutting-edge deep learning.

You will work with data scientists and product teams to translate research into production-ready solutions, optimize models for edge and cloud deployment, and mentor junior engineers.

Qualifications

• Master's or PhD in Computer Vision, ML, CS or related field.
• 4+ years of CV and deep learning model development.
• Proficiency with OpenCV, PyTorch, TensorFlow.
• Experience with COCO, ImageNet, KITTI datasets.

Responsibilities

• Design, implement, and optimize CV algorithms using classical techniques and deep learning.
• Work with datasets of images, videos, or 3D data to train and evaluate models.
• Build real-time vision pipelines for detection, tracking, recognition, and segmentation.
• Collaborate with data scientists, ML engineers, and product teams to integrate CV systems into products.
• Deploy models to edge devices, cloud environments, or embedded systems; ensure performance.

Skills

OpenCV

PyTorch

TensorFlow

Image processing

3D vision

Python

C++

CNNs / R-CNN / YOLO

ViT / Transformers

Deployment to edge and cloud

Education

Master's or PhD in Computer Vision, ML, CS

Tools

TensorRT

ONNX

Job description

About the job Senior Computer Vision Engineer

About the Role:
We are looking for a Senior Computer Vision Engineer to lead the design and deployment of intelligent vision-based systems. You will work on projects involving image and video analysis, object detection, tracking, segmentation, OCR, and 3D vision using state-of-the-art deep learning models.

Key Responsibilities:

• Design, implement, and optimize computer vision algorithms using classical techniques and deep learning.
• Work with datasets of images, videos, or 3D data (LiDAR, depth sensors) to train and evaluate models.
• Build real-time vision pipelines for tasks like detection, tracking, recognition, and segmentation.
• Research and apply SOTA models (CNNs, Transformers, GANs, etc.) for custom CV use cases.
• Collaborate with data scientists, ML engineers, and product teams to integrate CV systems into products.
• Deploy models to edge devices, cloud environments, or embedded systems depending on application.
• Ensure performance, accuracy, and efficiency of vision systems in production environments.
• Mentor junior engineers and guide the technical direction of CV projects.

Requirements:

• Master's or PhD in Computer Vision, Machine Learning, Computer Science, or a related field.
• 4+ years of experience in computer vision and deep learning model development.
• Strong expertise in OpenCV, PyTorch, TensorFlow, and popular CV libraries.
• Experience with image processing, feature extraction, and neural network architectures (CNNs, R-CNN, YOLO, Mask R-CNN, ViT, etc.).
• Hands-on experience with datasets like COCO, ImageNet, KITTI, or custom datasets.
• Strong coding skills in Python and C++ (optional but valuable).
• Knowledge of real-time processing, model compression, and deployment to mobile/edge (e.g., TensorRT, ONNX, TFLite).

Nice to Have:

• Experience with 3D vision, SLAM, LiDAR, or AR/VR applications.
• Familiarity with robotics, autonomous systems, or drone vision.
• Experience publishing papers or contributing to open-source CV projects.