I’m a Data Engineer Trainee at Coforge Ltd. with a strong interest in building practical solutions across Machine Learning, Generative AI, and modern Data Engineering.

My focus is on developing data-driven applications that connect data pipelines, cloud platforms, machine learning, and LLM-based applications.

• 💼 Data Engineer Trainee at Coforge Ltd.
• 🐍 Working primarily with Python and SQL
• 🤖 Exploring Machine Learning, Deep Learning, NLP and Generative AI
• 🧠 Building applications using LLMs, RAG, LangChain and LangGraph
• ☁️ Working with AWS and Microsoft Azure cloud services
• ❄️ Learning modern data platforms including Snowflake and Snowpark
• ⚡ Exploring scalable data processing with PySpark
• 🔄 Interested in ETL/ELT, data pipelines, data warehousing and cloud data engineering
• 📚 Continuously strengthening Data Structures, Algorithms, ML and system fundamentals

Artificial Intelligence
        │
        ├── Machine Learning
        ├── Deep Learning
        ├── NLP
        └── Generative AI
                │
                ├── LLMs
                ├── RAG
                ├── LangChain
                └── LangGraph

Data Engineering
        │
        ├── Python
        ├── SQL
        ├── ETL / ELT
        ├── PySpark
        ├── Data Warehousing
        └── Cloud Data Engineering
                │
                ├── AWS
                │   ├── S3
                │   └── IAM
                │
                ├── Microsoft Azure
                │   └── ADLS
                │
                └── Snowflake
                    └── Snowpark

SF-Capstone-Project

End-to-end cloud data engineering and data warehousing project focused on building a modern data platform using AWS and Snowflake.

Focus: Data Engineering • Cloud Data Engineering • ELT • Data Warehousing

Tech: Python • SQL • AWS S3 • AWS IAM • Snowflake • Snowpark

Digital-HR · Live Demo

Enterprise Generative AI and RAG-based HR Policy Assistant built for Coforge HR-India. Siya provides grounded answers from official HR policy documents, supports conversational follow-ups, and generates downloadable policy documents.

Focus: Generative AI • LLM • RAG • NLP • Conversational AI

Tech: Python • RAG • LLM • Streamlit • ChromaDB • Google OAuth • PDF Processing

Topic-Modeler · Live Demo

Interactive NLP and Machine Learning application for document topic discovery using LDA Topic Modeling and K-Means clustering, with visual insights and real-time prediction.

Focus: NLP • Machine Learning • Topic Modeling • Clustering

Tech: Python • NLP • LDA • K-Means • Scikit-learn • Streamlit

Pathshala

Modular College Management ERP designed to centralize academic and administrative workflows with role-based access for Admin, HOD, Faculty, and Students.

Focus: Backend Engineering • REST APIs • RBAC • Database Design • Full-Stack Development

Tech: Python • FastAPI • React • TypeScript • MySQL • REST API • RBAC

• Machine Learning Engineering
• Deep Learning & NLP
• Generative AI & LLM Applications
• Retrieval-Augmented Generation (RAG)
• LangChain & LangGraph
• PySpark & Distributed Data Processing
• Snowflake & Snowpark
• AWS Data Engineering
• Microsoft Azure & ADLS
• Data Warehousing
• ETL / ELT Pipelines
• Data Engineering Architecture

Build with data. Learn with curiosity. Engineer for scale.

Always learning. Always building. Always improving.