Camera Vision Engineer

DigiRecruitx; Pune District; On-site; INR 1,500,000 - 2,300,000; Full time

Job summary

DigiRecruitx is seeking a Camera Vision Engineer to develop real‑time video analytics and edge‑deployable pipelines for industrial and maritime use. You will implement sensor fusion, object detection, and OCR models, with hands‑on work on DeepStream, PyTorch, and OpenCV.

The role emphasizes deploying on Jetson‑class devices, Dockerized environments, and scalable architectures, leveraging PyQt dashboards and data streams (WebRTC, Kafka, Zookeeper, PostgreSQL).

Qualifications

• 2 to 4 years of experience in computer vision and video processing.
• Bachelor's degree in Computer Science, Electronics, AI/ML, or a related field.
• Expertise in Deep Learning including CNNs, YOLO, DETR v2, SAM2, and OCR.
• Proficiency in Python, C++, Bash Scripting, PyTorch, TensorRT, and ONNX Runtime.
• Hands‑on experience with OpenCV, DeepStream, GStreamer, and Edge Devices.
• Solid understanding of Docker, Linux, Git, Kafka, Zookeeper, and SQL databases.

Responsibilities

• Develop and optimize real‑time video analytics solutions using DeepStream, YOLO, PyTorch, and OpenCV.
• Build and deploy computer vision models for object detection, segmentation, tracking, OCR, and classification.
• Deploy scalable solutions on edge devices like the Jetson series using Docker, Linux, and GStreamer.
• Design sensor fusion pipelines and work with RTSP cameras, satellite imagery, and multi‑camera setups.
• Build user‑friendly dashboards using PyQt and handle architecture components like WebRTC, Kafka, Zookeeper, and PostgreSQL.
• Collaborate with cross‑functional teams for requirement gathering, testing, and deployment.

Skills

Computer Vision

Video Processing

Deep Learning

Edge Deployment

Education

Bachelor's degree in CS/EE/AI

Tools

Python

C++

Bash Scripting

PyTorch

TensorRT

ONNX Runtime

OpenCV

DeepStream

GStreamer

Docker

Linux

Git

Kafka

Zookeeper

SQL databases

Job description

Overview We are looking for a skilled Camera Vision Engineer to develop real-time camera vision pipelines, sensor fusion systems, and video analytics applications for industrial and maritime domains. The ideal candidate will have strong hands‑on experience in Deep Learning, video processing, and edge device deployment.

Key Responsibilities

• Develop and optimize real‑time video analytics solutions using DeepStream, YOLO, PyTorch, and OpenCV.
• Build and deploy computer vision models for object detection, segmentation, tracking, OCR, and classification.
• Deploy scalable solutions on edge devices like the Jetson series using Docker, Linux, and GStreamer.
• Design sensor fusion pipelines and work with RTSP cameras, satellite imagery, and multi‑camera setups.
• Build user‑friendly dashboards using PyQt and handle architecture components like WebRTC, Kafka, Zookeeper, and PostgreSQL.
• Collaborate with cross‑functional teams for requirement gathering, testing, and deployment.

Required Skills and Qualifications

• 2 to 4 years of experience in computer vision and video processing.
• Bachelor's degree in Computer Science, Electronics, AI/ML, or a related field.
• Expertise in Deep Learning including CNNs, YOLO, DETR v2, SAM2, and OCR.
• Proficiency in Python, C++, Bash Scripting, PyTorch, TensorRT, and ONNX Runtime.
• Hands‑on experience with OpenCV, DeepStream, GStreamer, and Edge Devices.
• Solid understanding of Docker, Linux, Git, Kafka, Zookeeper, and SQL databases.

Preferred Attributes

• Experience with ROS, PLC integration, and satellite image analysis.
• Familiarity with cloud platforms such as Azure or AWS EC2.
• Certifications like NVIDIA Jetson AI Specialist or Microsoft Azure.
• Published research or a strong hands‑on project portfolio.