Computer Vision Engineer

Trigvent Solutions; Mohali; On-site; INR 1,200,000 - 1,800,000; Full time

Job summary

Trigvent Solutions seeks an experienced computer vision engineer to build, train, and optimize DL models for object detection, segmentation, and facial recognition. You will develop high-throughput pipelines for live camera streams and optimize inference on cloud and edge hardware.

Proficiency in Python, OpenCV, and frameworks like PyTorch or TensorFlow is required, with hands-on experience in YOLO, Faster R-CNN, Detectron2, and Vision Transformers.

Qualifications

• 2+ years of professional experience in Computer Vision, Image Processing, and Deep Learning.
• Strong proficiency in Python, OpenCV, and deep learning frameworks (PyTorch or TensorFlow).
• Experience with vision architectures: YOLO (v8/v9/v10), Faster R-CNN, Detectron2, and Vision Transformers.
• Hands-on experience optimizing models for deployment (ONNX, TensorRT, FP16/INT8 quantization).
• Experience with Linux, Docker, and GPU cluster environments (CUDA / cuDNN).

Responsibilities

• Design, train, optimize, and deploy deep learning models for object detection, segmentation, and facial/image recognition.
• Build high-throughput real-time video analytics pipelines processing live RTSP and camera streams.
• Optimize computer vision inference speeds using TensorRT, ONNX Runtime, and OpenVINO for cloud and edge hardware.
• Develop synthetic data generation, automated annotation pipelines, and rigorous benchmarking protocols.
• Collaborate with backend and mobile engineers to package vision solutions into scalable client products.

Skills

Python

OpenCV

Deep Learning

PyTorch

TensorFlow

Education

Bachelor's or Master's in Computer Science/AI/Robotics

Tools

Linux

Docker

CUDA/cuDNN

ONNX Runtime

TensorRT

Job description

Job Description

• Design, train, optimize, and deploy deep learning models for object detection, segmentation, and facial/image recognition.
• Build high-throughput real-time video analytics pipelines processing live RTSP and camera streams.
• Optimize computer vision inference speeds using TensorRT, ONNX Runtime, and OpenVINO for cloud and edge hardware.
• Develop synthetic data generation, automated annotation pipelines, and rigorous benchmarking protocols.
• Collaborate with backend and mobile engineers to package vision solutions into scalable client products.

Skills & Experience

• 2+ years of professional experience in Computer Vision, Image Processing, and Deep Learning.
• Strong proficiency in Python, OpenCV, and deep learning frameworks (PyTorch or TensorFlow).
• Experience working with vision architectures: YOLO (v8/v9/v10), Faster R-CNN, Detectron2, and Vision Transformers.
• Hands-on experience optimizing models for deployment (ONNX, TensorRT, FP16/INT8 quantization).
• Experience with Linux, Docker, and GPU cluster environments (CUDA / cuDNN).

Qualifications

• Bachelors or Masters degree in Computer Science, Artificial Intelligence, Robotics, Electronics, or related discipline.

Disclaimer: This job posting has been aggregated from external source. Role details, content, and availability are subject to change. Applicants are advised to confirm the latest information directly on the company website before applying.