Headline

DS Analyst @ Tiger Analytics | IIT KGP '24

About

Hi! I am a final-year undergraduate at IIT Kharagpur in the Department of Aerospace Engineering. I am interested in Data Science and Artificial Intelligence.

Location

Patna

AI stack

claude

langchain

langgraph

openai

Microsoft Copilot

Pinecone

Work experience

AI ML Associate at Tiger Analytics, Aug 2024 - Present · 2 y, Hyderabad, Tiger Analytics : AIML Associate — Full Time (Jul’25 – Present) • Project: Knowledge Repository Management (RAG + text-to-SQL) • Architected a production-grade GenAI orchestration pipeline to analyze both structured and unstructured data for multi-node stateful agent workflows. • Engineered a Hybrid RAG and text-to-SQL routing engine that dynamically directs user queries based on intent detection; deployed a multi-stage text-to-SQL pipeline with recursive syntax validation (sqlglot), error-handling/debugging loops (3-retry backoff), and LLM-driven summarization agent for actionable business insights. • Enhanced response accuracy to 95% by developing a sophisticated prompt engineering framework, utilizing dynamic prompt selection, Chain-of-Thought (CoT) reasoning to minimize hallucinations and integrated JWT/OAuth2 authentication. • Developed and scaled secure RESTful APIs (FastAPI) for batch file uploads and natural language queries, asynchronous parallel processing to optimize chatbot latency, automated source referencing (hyperlink) with granular usage logging. Tiger Analytics : Data Science Analyst — Full Time (Jul’24 – Jun’25 ) • Project: Spendwise AI for BI Chatbot (RAAS Framework) | Python, Databricks, Azure, SQL, LLMs, FastAPI • Engineered an enterprise AI-for-BI chatbot across multiple business modules (TLC, Reshoring, GSS), deploying end-to-end NLU pipelines tailored to 4 distinct user personas. • Architected a secure data foundation in Databricks utilizing custom table views, UDFs, and granular Role-Based Access Control (RBAC) to enforce persona-based data access. • Developed 4 REST APIs using FastAPI and LangChain for AI Insight Pipelines, automating the generation of curated business insights and validating endpoints via Postman and Swagger. • Boosted LLM response accuracy from 70% to 98% for the text-to-SQL agent by translating complex PowerBI DAX queries into Ground Truth SQL and systematically optimizing few-shot prompt instructions. • Explored potential churners ahead of time with an accuracy score of 95.48% using XGBoost (SMOTE-ENN) classification

Data Analytics Project at Indian Institute of Management, Ranchi, Jul 2022 - Sep 2022 · 3 mos, Ranchi, Jharkhand, India

Amazon ML Summer School '22 at Amazon, Jul 2022 - Aug 2022 · 2 mos, - Selected in this integrated learning course with practical industry applications through an immersive experience with Amazon Scientist - Inculcated knowledge about some key ML topics including Supervised Learning, Deep Neural Networks, Dimensionality Reduction, Unsupervised Learning, Probabilistic Graphical Models, and Sequential Learning

Summer Research Intern at National Institute of Industrial Engineering, May 2022 - Aug 2023 · 1 yr 4 mos, Mumbai, Maharashtra, India, Working on projects involving operations research and logistics optimization using artificial intelligence

Data Science and Business Analytics Intern at The Sparks Foundation, Jul 2021 - Aug 2021 · 2 mos, Objective: To create a hybrid model for Stock Market Prediction and Sentiment Analysis of TOI News headlines

Research And Development Intern at iHub - AWaDH @ IIT Ropar, May 2021 - Jul 2021 · 3 mos, Precision Agriculture Project: To implement IP capabilities in the hoppers to detect anomalies in the paddy fields with weed classification

Education

Interdisciplinary Dual Degree ( B.Tech & M.Tech ), Aerospace Engineering + ML&AI applications, Indian Institute of Technology, Kharagpur