About

Curious about how complex things break down into simple parts.

I'm someone with an open mind, always learning and driven by curiosity about how complex things break down into simple, manageable parts. I have always try to put myself in situations where I had to solve some kind of problem, like hackathons or improving upon some inefficiency.

My experience spans software fundamentals to ML, generative AI, computer vision, analytics, data engineering, and visualization - learned through internships, coursework, and building things. This exposure to a wide range of areas has helped me develop a holistic understanding of how different components of a system interact and how to optimize them for better performance and efficiency.

Apart from my experinces and projects, the changelog shows how consistently I ship or try to work on learning/builing something. The honest notes on every project show how I think about tradeoffs. And how this site works is a concept I tried on this website to show the engineering standards I hold myself to. And if you want to know what's up with me right now, that's literally a page.

Technical forte

Software Engineering

Python, SQL, TypeScript/React, FastAPI, REST APIs, system fundamentals

AI & Data Systems

LLM pipelines, agentic AI & RAG, reinforcement learning, ML, computer vision

Infrastructure

Linux, Git, Docker, CI/CD, HPC/Slurm, Azure, AWS

Experience

Project 990

Jan 2026 - Present

AI Engineer

Designing and productionizing a multi-stage LLM pipeline on HPC that generates mission statements for 175,000+ nonprofits from IRS Form 990-EZ data, powering downstream analytics and grantor–grantee matching.

–Designed and deployed a 3-stage LLM pipeline on HPC using Mistral-7B for generation and Gemma-7B for evaluation across 175,000+ nonprofits.
–Built a fallback architecture integrating organization descriptions and grant-purpose data, raising mission-statement coverage from 50% to 93.5% across 163,700+ organizations.
–Productionized the pipeline with Slurm job scheduling, fault-tolerant checkpointing, and a config/model-agnostic design for end-to-end automated execution.

LLMs · HPC · Slurm · Mistral-7B · Python

Indiana University

Jan 2026 - May 2026

Mathematics Tutor

Tutored undergraduate students in mathematics - breaking dense concepts into simple, workable steps, one student at a time.

–Tutored undergraduates across core mathematics courses, adapting explanations to each student's way of thinking.

Calculus · Statistics · Problem Solving

Indiana University

Jun 2025 - Dec 2025

Research Assistant - AI in Cybersecurity

Researched multi-agent reinforcement learning for autonomous cyber defense in the CAGE Challenge 4 environment - training and evaluating agents that detect and respond to threats.

–Applied, trained, and evaluated RL algorithms from Stable-Baselines3 and RLlib in a multi-agent reinforcement learning (MARL) environment, CAGE Challenge 4.
–Designed reward-shaping strategies with additional reward signals to improve agent behavior, stability, and threat-detection performance in simulated adversarial scenarios.

Reinforcement Learning · MARL · Stable-Baselines3 · RLlib · PyTorch

Methix

Jun 2025 - Dec 2025

AI Developer Intern

Built an artist-management agentic AI system - a personal manager for music artists with retrieval, scheduling, and outreach capabilities on Azure.

–Developed an agentic AI system using Azure OpenAI and LangChain with tool-use capabilities: RAG across 100+ documents, scheduling, and outreach.
–Engineered the data retrieval layer for an AI search feature, writing SQL template queries to fetch and rank 200+ artist profiles against real-time user queries.
–Optimized AI pipelines and deployments in Azure AI Foundry by analyzing usage and storage tiers, reducing production cost by 20% while maintaining reliability.

Azure OpenAI · LangChain · Agentic AI · RAG · SQL

Parallel Wireless

Feb 2024 - Jul 2024

Software Engineering Intern

Debugged and resolved production defects in React and TypeScript applications, and automated GUI validation with Jest - improving stability, coverage, and frontend performance.

–Debugged and resolved production software defects in React and TypeScript applications, improving reliability and user experience in an Agile environment.
–Developed and maintained Jest unit-testing suites, improving application stability, test coverage, and frontend performance by 30%.

React · TypeScript · Jest · Agile

Krios Info Solutions

Feb 2023 - May 2023

Data Science Intern

Built a retail demand-forecasting system over 5+ years of daily sales data for 300+ SKUs, with Power BI dashboards that turned forecasts into stakeholder decisions.

–Cleaned and transformed 5+ years of daily sales data for 300+ SKUs using Python and Pandas into a model-ready dataset for demand forecasting.
–Improved forecasting accuracy by 10% through ensemble architectures and hyperparameter tuning via cross-validation and grid search.
–Designed and maintained 5+ interactive Power BI dashboards visualizing sales trends, seasonal patterns, and forecast accuracy for stakeholders.

Python · Pandas · Power BI · Time Series

Education

Indiana University, Bloomington

2024 - 2026 · GPA 3.9 / 4.0

M.S. in Data Science

Data Structures & Algorithms · Applied Machine Learning · Usable AI · Computer Vision · Information Visualization · Big Data Management · Database Technologies · Computer Networks · Statistics

academic record ↗

Savitribai Phule Pune University

2020 - 2024 · GPA 3.6 / 4.0

B.E. in AI and Data Science

Software Engineering · Data Structures & Algorithms · Machine Learning & Deep Learning · Big Data Analytics · Database Management Systems

academic record ↗

Recognition

NCAA Final Four Analytics Challenge - Winner 2026

Won by predicting tournament seedings for 360+ teams at 78% accuracy with a 7-model gradient-boosting ensemble over 104 engineered features, presented to NCAA stakeholders through Tableau dashboards.

InnoQuest 2025 - Honorable Mention 2025

Recognized by the Shoemaker Innovation Center at Indiana University for building an AI assistant builder that lets SMBs put AI on their own data in 3–4 simple steps.

GeeksforGeeks Hackathon - Winner 2023

Won with a personal finance app featuring AI-based voice-to-text expense logging and expense forecasting.

TEDx Curator 2023

Organized a TEDx event - coordinating speakers and logistics, delivering talks to an audience of 500+.