As an AI & Machine Learning Engineer, I am passionate about advancing Natural Language Processing (NLP) and Large Language Models (LLMs) to solve real-world problems and create engaging user experiences. My expertise spans from speech-to-speech translation and multilingual model fine-tuning to building scalable machine learning pipelines and developing Retrieval-Augmented Generation (RAG) systems for more intelligent and context-aware models.I have designed and implemented end-to-end ML pipelines that automate critical processes like voice cleaning, data annotation, model training, and evaluation. At HuroAI, I led the development of a real-time multilingual speech-to-speech model, reducing the Word Error Rate (WER) by 40% and bringing down translation latency to just 2 seconds per sentence. I also played a pivotal role in scaling models using GCP and Vertex AI, ensuring real-time performance across complex, large-scale datasets.In addition to model development, I have worked extensively with RAG frameworks, combining retrieval-based techniques with large language models to deliver highly accurate and contextually relevant responses for NLP tasks. I’ve built robust question-answering systems, document retrieval models, and multimodal architectures, leveraging PyTorch, Langchain, and transformer models. My projects in RAG and multimodal models have helped bridge the gap between structured and unstructured data, enabling more intelligent, real-time responses for various applications.From distributed training and transformer architecture optimization to fine-tuning sequence-to-sequence models and integrating retrieval-based learning, I am focused on creating scalable, efficient AI systems. I thrive on solving complex technical problems that push the boundaries of what AI can achieve in real-world scenarios.I believe that AI and machine learning have the potential to revolutionize industries, and I’m excited to contribute to that transformation by solving intricate challenges and deploying innovative, data-driven solutions at scale.If you’re looking for someone who can blend cutting-edge AI technologies like RAG, LLMs, and deep learning frameworks with practical, real-world applications, let’s connect! I’m always open to discussing exciting opportunities, collaborations, or ways to make AI systems more impactful and accessible.
