Job
Description
Job Summary: We are seeking a passionate and technically skilled AI / ML Engineer with 2+ years of hands-on experience in Computer Vision and Generative AI (GenAI). This role involves building and optimizing advanced visual intelligence systems leveraging PyTorch, OpenCV, transformers, and diffusion models. The ideal candidate will have experience in areas such as image segmentation, pose estimation, video inpainting, and synthetic data generation, along with exposure to LLM-prompt integration and datasets like DeepFashion2 and COCO. Key Responsibilities: Develop and deploy advanced computer vision models for tasks such as image segmentation, pose estimation, and video manipulation. Implement and experiment with Generative AI techniques, including diffusion models, GANs, and video inpainting. Leverage PyTorch, OpenCV, and modern deep learning frameworks to build scalable vision pipelines. Integrate LLM-based prompting into visual workflows and multimodal applications. Utilize datasets such as DeepFashion2, COCO, and custom synthetic datasets for model training and validation. Optimize model inference for performance, latency, and resource efficiency in production environments. Collaborate with data scientists, product engineers, and designers to deliver intelligent visual features in end-user applications. Qualifications: 2+ years of experience in machine learning and computer vision. Proficiency with PyTorch, OpenCV, and relevant deep learning libraries. Hands-on experience with image segmentation, pose estimation, or video-based vision tasks. Understanding of diffusion models, GANs, and transformer-based architectres. Knowledge of LLM prompt engineering and multimodal integration. Experience working with structured datasets like COCO and DeepFashion2. Strong debugging, analytical, and performance optimization skills. Preferred Qualifications : Experience in synthetic data generation and domain-specific data augmentation. Familiarity with model quantization, pruning, or other inference optimization techniques. Exposure to MLOps tools and cloud-based model deployment (e.g., AWS Sagemaker, GCP AI Platform). Contributions to open-source projects or published research in computer vision or generative models. Location: Pan- Bengaluru,Hyderabad,Delhi / NCR,Chennai,Pune,Kolkata,Ahmedabad,Mumbai
