I am a passionate Machine Learning Engineer and Backend Developer with strong expertise in Machine Learning, Computer Vision, LLMs (Large Language Models), and scalable API development. I hold an M.Tech from IIT Bombay in Systems and Control Engineering, where I built a solid foundation in optimization, machine learning, and intelligent control systems. Throughout my time at ZF India Pvt Ltd, I have worked on a wide range of projects. I developed and deployed object detection models such as YOLO and Faster R-CNN using PyTorch for car driving datasets. I also built peak pressure prediction models and NVH analysis tools that contributed to more accurate automotive system predictions. Additionally, I led the development of a full-stack document understanding platform, extracting structured data from complex PDF test reports by combining Llama-based prompting, Azure Document Intelligence, and FastAPI-driven APIs. My technical skill set includes Python, PyTorch, TensorFlow, Keras, Scikit-Learn, LangChain, FastAPI, OpenShift, MinIO, MongoDB, and ONNX for model optimization and scalable deployment. I have extensive experience working with LLMs such as Llama 3.1, Llama 3.2 Vision, and Transformer-based architectures like BERT, along with backend systems designed for large-scale image and document processing. I have been engaged in Retrieval-Augmented Generation (RAG) systems development. I explored building RAG pipelines using LangChain integrated with Llama 3.2 Vision and OpenAI APIs. I worked on custom vector stores and hybrid retrieval techniques combining semantic and keyword searches, designed prompt chaining strategies to enhance dynamic conversation flows, and built multi-modal RAG systems integrating text and image data for richer document QA experiences. I look forward to contributing to innovative projects at the intersection of Machine Learning, GenAI, and scalable system design