Computer Vision & AI Deployment Engineer

We are looking for a Computer Vision & AI Deployment Engineer to join our team and work on real-time AI-powered video analytics and CCTV monitoring systems.

The ideal candidate will have hands-on experience developing and deploying computer vision solutions for real-world video streams, including object detection, tracking, face recognition, license plate recognition, and multi-camera AI systems.

This role combines Computer Vision development with Field Deployment Engineering (FDE). You will be involved not only in developing AI models and inference pipelines but also in deploying, configuring, monitoring, and troubleshooting AI systems connected to IP cameras and GPU servers.

Key Responsibilities

• Develop and deploy real-time computer vision applications for CCTV/IP camera streams.
• Work with RTSP video streams, IP cameras, NVRs, and CCTV infrastructure.
• Implement object detection, tracking, face recognition, vehicle detection, and license plate recognition.
• Work with YOLO/Ultralytics, OpenCV, PyTorch, ONNX Runtime, and related computer vision frameworks.
• Optimize AI inference for NVIDIA GPUs using CUDA and, where appropriate, TensorRT.
• Develop scalable video-processing pipelines capable of handling multiple camera streams.
• Implement tracking solutions such as ByteTrack, DeepSORT, or similar technologies.
• Integrate AI services with backend APIs and databases.
• Develop and maintain AI inference APIs using technologies such as FastAPI.
• Monitor FPS, GPU utilization, memory usage, latency, and system stability.
• Troubleshoot RTSP connectivity, camera failures, network issues, GPU problems, and AI inference failures.
• Deploy AI systems on Linux/Ubuntu servers and edge computing systems.
• Configure and maintain production AI services.
• Perform on-site/field deployments and troubleshoot hardware, networking, camera, and software issues.
• Work with development and backend teams to integrate AI functionality into larger software platforms.
• Maintain technical documentation for deployments, configurations, and troubleshooting procedures.
• Continuously improve system performance, reliability, and scalability.

Required Technical SkillsComputer Vision & AI

• Strong Python programming skills.
• Hands-on experience with OpenCV.
• Practical experience with YOLO / Ultralytics or similar object detection frameworks.
• Experience with PyTorch.
• Understanding of object detection, tracking, image processing, and video analytics.
• Experience working with real-time video streams.
• Understanding of deep learning inference and model optimization.

AI Deployment

• Experience with NVIDIA GPUs and CUDA.
• Experience with ONNX / ONNX Runtime.
• Knowledge of TensorRT is highly preferred.
• Experience optimizing AI models for real-time inference.
• Understanding of GPU memory, FPS, latency, and resource utilization.

CCTV & Field Deployment

• Experience working with IP cameras and RTSP streams.
• Understanding of CCTV/NVR systems.
• Knowledge of ONVIF is a plus.
• Basic to strong understanding of networking, TCP/IP, LAN, PoE, and network troubleshooting.
• Experience deploying software on Ubuntu/Linux servers.
• Ability to troubleshoot systems remotely and on-site.
• Willingness to travel to customer/project sites when required.

Preferred Experience

Experience with any of the following will be a strong advantage:

• Face recognition
• Person re-identification (ReID)
• License Plate Recognition (LPR/ANPR)
• Vehicle detection and tracking
• Multi-camera tracking
• ByteTrack / DeepSORT
• InsightFace / FaceNet / SFace
• PaddleOCR
• FastAPI
• PostgreSQL
• Nginx
• PM2 / systemd
• Docker
• Edge AI
• NVIDIA Jetson
• TensorRT
• CCTV analytics
• Security/surveillance AI systems

Qualifications

• Bachelor's degree in Computer Science, Software Engineering, Artificial Intelligence, Electrical Engineering, or a related field.
• 2+ years of hands-on experience in Computer Vision, AI/ML, or video analytics.
• Strong problem-solving and debugging skills.
• Ability to work independently on production systems.
• Good communication and documentation skills.
• Willingness to work in field environments when required.

What We Are Looking For

We are looking for someone who can take a computer vision solution from development to production deployment.

The ideal candidate should be comfortable working with:

Camera → RTSP → Video Processing → AI Detection → Tracking → Recognition → Event Generation → API → Database → Dashboard

You should be able to diagnose problems when a camera stops streaming, FPS drops, GPU memory increases, an AI model fails, or a production server becomes unstable.

Candidates with only academic/research experience and no practical deployment experience are less suitable for this role.

Hiring Process

Shortlisted candidates may be asked to complete a practical technical assessment involving:

• RTSP video processing
• YOLO/object detection
• Object tracking
• GPU inference
• Computer vision pipeline design
• Production deployment and troubleshooting

Why Join Us?

• Work on real-world AI and computer vision systems.
• Work with large-scale CCTV and video analytics deployments.
• Gain experience with NVIDIA GPU infrastructure and real-time AI.
• Work on challenging problems involving multi-camera video analytics.
• Opportunity to contribute to production-grade AI products from development through deployment.

To Apply: Please submit your CV along with examples/GitHub links of relevant Computer Vision, AI, CCTV, or video analytics projects.

Pay: Rs50,000.00 - Rs60,000.00 per month

Work Location: Hybrid remote in Islamabad