Headline

System Engineer @ TCS | AI & Data Engineer | Databricks Certified | AI & Data Pipelines | M.Tech AI & DS (IIT Patna ’27)

About

AI & Data Engineer with hands-on experience building scalable AI and data solutions using Python, SQL, Databricks, PySpark, and Generative AI. My work focuses on LLM-powered applications and data pipelines, including Retrieval-Augmented Generation (RAG), vector search, LLM enrichment, document processing, embeddings, and asynchronous LLM workflows. In my current role at TCS, I work on AI and data engineering initiatives involving unstructured data, document processing, hierarchical chunking, embeddings, vector search, and scalable AI processing pipelines. I have hands-on experience with Databricks, Mosaic AI, Unity Catalog, Delta Lake, Azure OpenAI, LangChain, Flask, REST APIs, and async programming. I have worked on large-scale AI processing workflows involving 250,000+ document chunks, along with AI-powered knowledge and retrieval systems for enterprise use cases. Currently pursuing an M.Tech in Artificial Intelligence & Data Science from IIT Patna, while expanding my expertise across Generative AI, Machine Learning, Agentic AI, distributed systems, and cloud-based AI solutions. Interested in building reliable, scalable AI systems that solve real-world problems.

Location

Atmakur

AI stack

langgraph

openai

Work experience

System Engineer at Tata Consultancy Services, Sep 2024 - Present · 2 yrs 2 mos, Greater Bengaluru Area, • Built a SQL Query Generation Bot using Python and LangChain to automate query creation from structured inputs, reducing manual effort and improving developer productivity • Designed a custom chunking and preprocessing strategy to handle large-scale datasets, enabling efficient LLM input handling and improving response accuracy • Implemented asynchronous LLM processing using asyncio with semaphore-based concurrency control, reducing LLM request and response generation time by ~60% by enabling parallel execution across distributed workloads • Developed retry mechanisms with exponential backoff and robust error handling (rate limits, API timeouts, content filters), ensuring reliability in production-like environments • Worked on Databricks to build scalable data pipelines using distributed processing techniques, handling large datasets with optimized transformations • Developed embedding-based retrieval workflows for intelligent data access and context-aware query generation • Integrated logging and monitoring mechanisms for tracking query generation, failures, and performance metrics • Collaborated on building end-to-end AI-powered data workflows, combining data engineering and LLM capabilities for real-world use cases Tech Stack: Python, SQL, LangChain, Databricks, AsyncIO, Azure OpenAI, Pandas

Education

Master of Technology - MTech, Artificial Intelligence and Data Science, Indian Institute of Technology, Patna

B.Tech, ECE, Shanmugha Arts, Science, Technology & Reserch Academy (SASTRA), Thanjavur