AI/ML Engineer – Computer Vision & Video Analytics with 2 to 8 years of experience

Company Description

Cydez Technologies, located in Kochi, Kerala, is a prominent IT Digital Transformation and IT Service Management company. The organization specializes in providing innovative digital solutions to help businesses streamline operations and achieve exceptional efficiency. By leveraging advanced technologies and customized IT strategies, Cydez Technologies assists organizations in overcoming the complexities of the digital landscape while offering exceptional service and robust management solutions.

We are seeking a highly skilled AI/ML Engineer to design, build, and deploy realtime computer vision systems for safety monitoring using IP cameras. The role involves developing deep learning models, building video processing pipelines, optimizing models for edge deployment, and integrating AI systems with backend services and dashboards.

Key Responsibilities

• Design and implement computer vision models for safety monitoring using video streams.
• Develop realtime AI pipelines for processing RTSP camera feeds.
• Train and finetune object detection models (e.g., PPE detection, fire/smoke detection).
• Implement object tracking for people counting and behavior monitoring.
• Integrate AI models with backend APIs and realtime dashboards.
• Optimize models for production using TensorRT or ONNX runtime.
• Collaborate with backend, frontend, and DevOps teams to deploy scalable AI systems.
• Evaluate model performance using metrics such as mAP, precision, and recall.

Required Technical Skills

• Strong programming skills in Python.
• Deep learning frameworks: PyTorch or TensorFlow.
• Computer Vision libraries: OpenCV, PIL, scikit-image.
• Experience with object detection models such as YOLO.
• Experience working with video streams and RTSP cameras.
• Knowledge of model optimization using ONNX and TensorRT.
• Experience working with Linux and GPU environments (CUDA).

Data & ML Skills

• Dataset collection, labeling, and preprocessing.
• Experience with annotation tools such as CVAT or Roboflow.
• Data augmentation techniques for improving model performance.
• Model evaluation using confusion matrix, precision, recall, and mAP. Video & RealTime Processing
• Experience with video processing pipelines using OpenCV and FFmpeg.
• Knowledge of realtime frame extraction and inference pipelines.
• Experience implementing object tracking algorithms such as ByteTrack or DeepSORT.
• Understanding of pose estimation and behavior detection techniques.

Backend & System Integration

• Experience building APIs using FastAPI or Flask.
• Understanding of REST APIs and WebSocket communication.
• Experience integrating AI outputs with dashboards and monitoring systems.
• Knowledge of PostgreSQL and Redis for storing detections and analytics.

Deployment & Infrastructure

• Experience with Docker and containerized deployments.
• Knowledge of Linux server environments.
• Experience deploying AI models on GPU servers or edge devices.
• Understanding of CI/CD and monitoring systems for AI services.

Nice to Have

• Experience building multicamera video analytics systems.
• Knowledge of WebRTC, HLS, or MJPEG streaming.
• Experience with edge AI devices such as NVIDIA Jetson.
• Experience deploying AI systems in industrial or safety environments.

Qualifications

• Bachelor’s or Master’s degree in Computer Science, Artificial Intelligence, Machine Learning, or related field.
• 2+ years of experience in machine learning or computer vision engineering.
• Experience working on production AI systems is highly preferred.