Generative Ai Engineer
Current• Led the implementation of Deep Dream algorithms for image enhancement and modification, leveraging Meta Deep Dream technology. • Applied deep neural networks to analyze and modify images, creating visually striking and artistically unique results. • Successfully integrated real-time Style Transfer algorithms into interactive applications, allowing users to apply artistic styles to images and videos on-the-fly. • Optimized algorithms for efficiency, ensuring smooth and responsive user experiences in real-time environments. • Fine-tuned pre-existing Style Transfer models to align with project-specific artistic preferences and requirements. • Customized model parameters and architectures to achieve desired visual effects, demonstrating a deep understanding of the underlying neural network structures. • Implemented optimization techniques to enhance the speed and efficiency of Deep Dream and Style Transfer algorithms. • Employed parallel processing and GPU acceleration to achieve real-time performance in resource-constrained environments. • Designed and implemented user-friendly interfaces for applications incorporating Deep Dream and Style Transfer, ensuring seamless and intuitive user interactions. • Conducted experiments with different neural network architectures, loss functions, and hyperparameters to explore and implement improvements in Deep Dream and Style Transfer outcomes. • Built different use cases and extensively worked on Jupyter Notebook for Data Cleaning, converted data into structured format, removed outliers, dropped irrelevant columns & missing values, imputed missing values with median/mode/average/min/max other statistical methods. • Developed and implemented Transformer-based models, such as GPT (Generative Pre-trained Transformer) or BERT (Bidirectional Encoder Representations from Transformers), for specific natural language processing (NLP) tasks.
