Computer Vision Engineer

Computer Vision Engineer

Should have the hands on experience to train computer vision and deep learning models to solve computer vision use cases. • Should be able to create and optimize algorithms for image and video analysis, for tasks such as object detection, image recognition, segmentation and video analytics. • Should have expertise on different object tracking algorithms and track multi objects in multi cameras. • Should be able to articulate camera calibration and region of interest extraction. • Should have experience working on a large-scale implementation with 100+ stream in real time • Fine-tune deep learning models like CNNs, vision transformers using frameworks such as Tensorflow, PyTorch, onnx etc. • Should have used NVIDIA frameworks preferably like NGC models, TAO toolkit, metropolis Deep stream, triton server, and triton server to create inferencing pipeline and its deployment. • Should have knowledge of optimizing inferencing pipelines to work on edge • Should be able to perform necessary pre and post processing to optimize the computer vision models and evaluate it. • Should have experience working on action recognition with temporal analysis • Should have knowledge on pruning the model for deploying on edge/ARM devices • Collaborate with Business and IT teams