Computer Vision Engineer

Ranchhill Software Solutions; Hyderabad; On-site; INR 2,500,000 - 4,500,000; Full time

Job summary

NAVA Vision AI in Hyderabad is seeking a skilled Computer Vision Engineer with 6-11 years of hands-on CV experience. You will design, train, and optimize CV/DL models, building object detection, tracking, OCR, and activity recognition solutions.

Collaborate across teams and contribute to production deployments, ensuring robust, scalable AI systems. Proficiency in Python and frameworks like PyTorch/TensorFlow, OpenCV, and YOLO is required.

Qualifications

• 6-11 years of hands-on Computer Vision experience.
• Strong Python programming skills.
• Good understanding of Deep Learning fundamentals.
• Experience with OpenCV, PyTorch and/or TensorFlow.
• Familiarity with YOLO and object detection.
• Experience with model training, evaluation, and optimization.

Responsibilities

• Design, develop, train, and optimize CV and DL models.
• Build object detection, tracking, segmentation, OCR, and activity recognition.
• Work with YOLO, OpenCV, TensorFlow, PyTorch, and related frameworks.
• Improve model accuracy for production deployments.
• Develop video analytics pipelines for CCTV/IP streams.
• Optimize inference for edge devices and cloud.
• Collaborate with Product, Solutions, and Engineering teams.
• Debug and improve AI model performance with real customer data.
• Participate in deployments, testing, and validation.
• Maintain model documentation and deployment best practices.

Skills

Computer Vision

Python

Deep Learning

OpenCV

PyTorch

TensorFlow

YOLO

Object Detection

Image Classification

Instance Segmentation

OCR

Video Analytics

Git

Debugging

Education

B.E./B.Tech./M.Tech in Computer Science/AI/Electronics/Data Science

Tools

Docker

Kubernetes

TensorRT

ONNX Runtime

AWS Services

NVIDIA Jetson

Job description

Computer Vision Engineer (6-11 Years Experience)

Location: Hyderabad (Work from Office)

Experience: 6-11 Years

Employment Type: Full-Time

About NAVA Vision AI

NAVA Vision AI is building an AI-powered computer vision platform that helps manufacturing plants, warehouses, logistics facilities, and industrial enterprises improve safety, operational efficiency, compliance, and asset visibility using existing CCTV cameras.

We build production-ready Vision AI solutions that solve real-world operational challenges across industries including manufacturing, logistics, distribution centers, retail, and smart infrastructure.

If you're passionate about solving real business problems using AI instead of building research prototypes, we'd love to hear from you.

Roles & Responsibilities

• Design, develop, train, and optimize Computer Vision and Deep Learning models.
• Build object detection, tracking, segmentation, OCR, and activity recognition solutions.
• Work with YOLO, OpenCV, TensorFlow, PyTorch, and related frameworks.
• Improve model accuracy for production deployments.
• Develop video analytics pipelines for CCTV and IP camera streams.
• Optimize inference for edge devices and cloud deployments.
• Work closely with Product, Solutions, and Engineering teams to deliver customer projects.
• Debug and improve AI model performance using real customer datasets.
• Participate in customer deployments, testing, and validation.
• Maintain model documentation and deployment best practices.

Required Skills

• 6-11 years of hands-on Computer Vision experience.
• Strong Python programming skills.
• Good understanding of Deep Learning fundamentals.
• OpenCV
• PyTorch and/or TensorFlow
• YOLO (v5/v8/v11 preferred)
• Object Detection
• Image Classification
• Instance Segmentation
• OCR
• Video Analytics
• Experience with model training, annotation, evaluation, and optimization.
• Familiarity with Git and collaborative software development.
• Good debugging and problem-solving skills.

Good to Have

• Experience with NVIDIA Jetson devices.
• TensorRT optimization.
• ONNX Runtime.
• Docker and Kubernetes.
• AWS services.
• RTSP/IP Camera integrations.
• Multi-camera video analytics.
• Tracking algorithms (DeepSORT, ByteTrack, BoT-SORT).
• LLM or Vision-Language Models.
• Experience working on industrial, warehouse, manufacturing, retail, or logistics Vision AI projects.

Education

B.E./B.Tech/M.Tech in Computer Science, Artificial Intelligence, Electronics, Data Science, or related field.