Computer Vision Engineer

Vivasha AI; New Delhi; Hybrid; INR 1.000.000 - 1.800.000; Vollzeit

Benefits dieser Stelle

Hybrid work

Paid leave and holidays as per policy

Zusammenfassung

Vivasha AI Solutions, based in New Delhi, is seeking a Computer Vision Engineer to develop intelligent visual recognition, object detection, image analysis, and video analytics systems for CCTV analytics, aerial imagery, automated inspection, and AI-assisted monitoring.

We require 2–5 years of CV/deep learning experience, strong Python and OpenCV skills, and hands-on PyTorch with model training or fine-tuning. Hybrid work arrangement is available for this role.

Qualifikationen

• 2–5 years of experience in computer vision or deep learning.
• Strong Python and OpenCV skills.
• Experience with PyTorch and training or fine-tuning deep learning models.
• Understanding of GPU acceleration and computer vision evaluation metrics.

Aufgaben

• Develop and optimize object detection, classification, tracking, and segmentation models.
• Work with YOLO-based architectures and OpenCV for image and video processing.
• Prepare annotation datasets and implement data augmentation pipelines.
• Evaluate precision, recall, mAP, inference speed, and deployment performance.
• Develop real-time video analytics and batch image processing pipelines.
• Optimize GPU inference and memory usage for deployment environments.
• Integrate computer vision models into Python applications and REST APIs.
• Investigate model errors and improve robustness under challenging visual conditions.

Kenntnisse

Python

OpenCV

PyTorch

Object detection

Video analytics

REST APIs

GPU acceleration

YOLO

Tools

YOLO

Jobbeschreibung

AI Research and Development New Delhi, India Full-Time Hybrid

Experience 2 - 5 Years

Compensation INR 1,000,000 - 1,800,000

Notice Period Immediate to 30 Days

Openings 2 Open Roles

Job Description

About the role

Vivasha AI Solutions is seeking a Computer Vision Engineer to develop intelligent visual recognition, object detection, image analysis, and video analytics systems. You will work on practical applications involving CCTV analytics, aerial imagery, automated inspection, and AI-assisted monitoring.

Responsibilities

• Develop and optimize object detection, classification, tracking, and segmentation models.
• Work with YOLO-based architectures and OpenCV for image and video processing.
• Prepare annotation datasets and implement data augmentation pipelines.
• Evaluate precision, recall, mAP, inference speed, and deployment performance.
• Develop real-time video analytics and batch image processing pipelines.
• Optimize GPU inference and memory usage for deployment environments.
• Integrate computer vision models into Python applications and REST APIs.
• Investigate model errors and improve robustness under challenging visual conditions.

Requirements

• 2-5 years of experience in computer vision or deep learning.
• Strong Python and OpenCV skills.
• Practical experience with object detection, segmentation, and tracking.
• Experience with PyTorch and training or fine-tuning deep learning models.
• Understanding of GPU acceleration and computer vision evaluation metrics.
• Opportunity to build real-world computer vision products.
• Work with GPU-accelerated AI development workflows.
• Hybrid work flexibility.
• Technical ownership and opportunities to influence product architecture.
• Professional development and knowledge-sharing opportunities.
• Paid leave and holidays as per company policy.

Required Skills

Preferred Skills