• Engineered a comprehensive car service history summary system utilizing Natural Language Processing (NLP), Large Language Models (LLM), and LangChain to establish a robust data memory chain and intricate connections.

• Built LLM-powered chatbot that seamlessly integrates OpenAI and Azure to deliver real-time responses, while simultaneously performing intent recognition and maintaining conversation context through LangChain Model• Designed an end-to-end XTTS model, leveraging GPU to minimize latency. Additionally, develop a FastAPI for deployment on EC2 instance. Leveraged AWS Sagemaker for GPU instance deployment for real-time application.• Developed a propensity model for Paytm Deals using ML Gradient Boosting (XGBoost) algorithm, achieving 85 % accuracy and enabling precise targeting of promotions, leading to a 15% increase in customer conversions• Worked on New customer acquisition through Paid channels and offering business solutions using Pyspark & AWS• Built a price prediction model for Paytm-soundbox using a decision trees model, further provided analysis on soundbox complaints and requirements on a Geo-level, improving resource allocation and customer satisfaction.

• Conceptualized techniques & methods to create a patentable product on the topic “Low-Cost Refrigeration System for small farmers”• Analyzed 20+ patent searches for pre-existing models to examine the reach of solutions available in the market and the scope of new doings• Created a HAVAC standard high efficiency with a 40% low-cost model and used standard material information from a cold-storage system• Modeled & performed Flow Simulation, DATA analysis, and Parameter analysis on the refrigeration market and components for quality check and B2B model.