Computer Vision Engineer

Computer Vision Engineer

Job Summary

We are seeking an experienced Computer Vision Engineer to join our Video Analytics team. In

this role, you will develop advanced AI-powered surveillance solutions for security applications

across various environments. Working collaboratively with cross-functional teams, you'll be

responsible for creating sophisticated algorithms that enhance security through vehicle analysis,

intrusion detection, behavioral monitoring, and object recognition in real-world security

environments.

Key Responsibilities

● Develop and optimize computer vision algorithms for security surveillance applications

● Work actively as part of the Computer Vision and Deep Learning team to train and

fine-tune models

● Collaborate closely with the Data Science team for appropriate dataset curation and

quality management

● Implement state-of-the-art architectures to improve detection accuracy and reduce false

positives

● Solve challenging problems by fine-tuning models with large-scale datasets

● Create efficient processing pipelines for real-time analysis of multiple video streams

● Integrate computer vision systems with existing security infrastructure

● Work with the R&D team to continuously improve model accuracy and precision for

CCTV camera deployments

● Develop adaptive algorithms that perform reliably in various lighting and weather

conditions

● Establish comprehensive testing methodologies to validate detection performance

Required Qualifications

● Bachelor's degree in Computer Science, Computer Engineering, or related technical field

● 2+ years of hands-on experience developing computer vision applications

● Strong programming skills in Python (mandatory)

● Proficiency in training detection/classification/segmentation models with

TensorFlow/PyTorch

● Strong understanding of model training dynamics with the ability to troubleshoot based

on training/evaluation metrics

● Good theoretical and practical knowledge of deep learning fundamentals (CNNs,

regularization techniques, etc.)

● Experience with real-time video processing and optimization techniques

● Understanding of dataset quality requirements for computer vision applications

Preferred Qualifications

● Programming experience in C++ (good to have)

● Experience with model optimization frameworks like OpenVINO and TensorRT

● Working knowledge of edge computing devices including Raspberry Pi and Jetson

devices

● Experience specifically with security and surveillance applications

● Familiarity with state-of-the-art models including YOLO-series, EfficientNet/EfficientDet,

etc.

● Knowledge of edge computing for video analytics

● Experience with multi-camera tracking and fusion algorithms

● Familiarity with CCTV systems and integration approaches

● Previous work on commercial security products

● Experience with anomaly detection in video streams

● Experience using Docker containers for Computer Vision/Deep Learning deployments

Technical Skills

● Computer Vision: OpenCV, image processing, feature extraction, spatial analysis

● Deep Learning: CNN architectures (YOLO, SSD, Faster R-CNN, EfficientDet), model

training and fine-tuning

● Video Processing: Real-time frame analysis, motion detection, multi-object tracking

● Programming: Python (mandatory), C++ (good to have)

● ML Frameworks: PyTorch, TensorFlow with model deployment experience

● Model Optimization: OpenVINO, TensorRT for edge deployment

● Edge Platforms: Experience with Raspberry Pi, Jetson Devices (good to have)

● Dataset Management: Data curation, augmentation, and quality control

● Development Tools: Git, Docker, CI/CD pipelines

● Edge Computing: Deployment on embedded systems and edge devices