3 Yolov5 Jobs

As an AI Engineer at Smartan FitTech, you will play a pivotal role in spearheading the design, development, and deployment of cutting-edge computer vision models aimed at enhancing human motion understanding and video analytics. You will be at the forefront of the AI development lifecycle, contributing to the implementation of features that power our innovative fitness intelligence systems. This role requires a strong engineering focus on real-world deployment, performance optimization, and scalability, rather than academic prototyping. Your responsibilities will include overseeing the complete lifecycle of computer vision models, from initial experimentation to deployment and ongoing monitoring. You will be tasked with constructing and refining deep learning models for various applications such as pose estimation, activity recognition, and posture correction. Leveraging techniques like transfer learning, fine-tuning, and knowledge distillation will be essential for achieving optimal performance and generalization. Additionally, you will be responsible for designing scalable data pipelines for video ingestion, annotation, preprocessing, and augmentation, as well as integrating AI modules into cloud-based environments using REST APIs or microservices. To excel in this role, you should possess a Bachelor's or Master's degree in computer science, AI, machine learning, or a related field, along with at least 2 years of experience deploying computer vision models in production environments. Proficiency in Python, particularly with PyTorch and/or TensorFlow, is crucial. Hands-on expertise with models like YOLOv5/YOLOv8, Vision Transformers, ResNet, and others, as well as experience with pose estimation frameworks and real-time motion tracking, will be highly beneficial. Familiarity with tools like OpenCV, MMAction2, DeepSort, and ONNX/TensorRT is also desired. In this role, you will have the opportunity to shape the future of intelligent fitness systems, with autonomy and ownership over the deployment of models that have a real-world impact. You will thrive in a fast-paced environment that offers exposure to the entire AI pipeline, from data processing to deployment, within a collaborative team culture that values engineering excellence and innovation.,

As an AI Computer Vision Engineer with 4+ years of experience, you will be responsible for developing and training computer vision models for various tasks such as object detection, image classification, and face recognition. You will optimize models for performance on edge devices and apply data augmentation techniques to image/video datasets. Additionally, you will need proficiency in Large Language Models and a strong understanding of statistical analysis and machine learning algorithms. Your role will involve hands-on implementation of machine learning algorithms like linear regression, logistic regression, decision trees, and clustering algorithms. Understanding image processing concepts and experience in model optimization, quantization, or deploying to edge devices will be essential. You should have strong programming skills in Python (or C++) and expertise in implementing and optimizing machine learning pipelines for seamless integration into production systems. Experience with real-time computer vision applications, OpenCV, NumPy, PyTorch/TensorFlow, and computer vision models like YOLOv5, Mask R-CNN will be beneficial. Engaging with multiple teams, contributing to key decisions, and providing solutions that apply across multiple teams are expected from you. You will lead the implementation of large language models in AI applications and research cutting-edge AI techniques to enhance system performance. Contribution to the development and deployment of AI solutions across various domains is also part of your responsibilities. In terms of requirements, you should design, develop, and deploy ML models for OCR-based text extraction, table and line-item detection, and named entity recognition. Evaluating and integrating third-party OCR tools, developing pre-processing and post-processing pipelines for image/text data, and familiarity with video analytics platforms are necessary skills. Experience with MLOps tools, academic CV research, and knowledge of GPU acceleration or hardware integration will be advantageous for this role.,

As a Computer Vision Intern, you will be responsible for assisting in building and refining the image recognition pipeline. Your role will involve tasks such as dataset management, image collection, annotation validation, dataset cleaning, and preprocessing. Once the foundational data work is completed, you will gain hands-on experience in model training, augmentation, and evaluation, directly contributing to our production-ready pipeline. Your responsibilities will include organizing, cleaning, and preprocessing large-scale retail image datasets, validating and managing annotations using tools like Roboflow, CVAT, or LabelImg, applying augmentation techniques, preparing datasets for training, supporting in training YOLOv5/YOLOv8-based models on custom datasets, running model evaluations, collaborating with the product team to enhance real-world inference quality, and documenting the dataset pipeline while sharing insights to improve data quality. We are looking for individuals who have a basic understanding of Computer Vision concepts such as Object Detection and Classification, familiarity with Python libraries like OpenCV, Pandas, NumPy, knowledge of image annotation tools like Roboflow, LabelImg, CVAT, and the ability to manage and organize large datasets. Experience with YOLOv5 or YOLOv8 (Training, Inference, Fine-tuning), exposure to image augmentation techniques like Albumentations, understanding of retail/commercial shelf datasets or product detection problems, and previous internship or project experience in computer vision would be considered advantageous for this role.,