YM
Open to full-time opportunities

DATA SCIENTIST · AI/ML ENGINEER

Building intelligent systems that connect AI, data, and real-world decisions.

I build intelligent systems, data products, and reliable AI applications that connect language models with databases, APIs, knowledge graphs, and real-world workflows.

Explore my work GitHub
College Park, MarylandMSIS @ UMD
Yash Mahajan
5Professional Experiences
4Featured Projects
2+Years Across Data, AI & Cloud
3Industry Domains

01 · About

I like building systems that are useful, explainable, and grounded in real data.

I am a Data Scientist and AI Engineer from Mumbai, pursuing an M.S. in Information Systems at the University of Maryland.

My work spans agentic AI, machine learning, data engineering, software development, cloud infrastructure, and intelligent automation. I am especially interested in systems that combine language models with structured databases, vector search, knowledge graphs, APIs, and validation layers.

Outside technology, I am usually following football and cricket, supporting Real Madrid and Team India, working out, or exploring new places to eat.

02 · Experience

Building across product engineering, applied AI, research, consulting, and cloud.

Software & Data Engineering Intern

Wave Automate LLC

  • Analyze 500+ synthetic healthcare call records and large application schemas using SQL and GCP data to support client-facing analytics.
  • Develop and test JavaScript/TypeScript product features for call reporting, customer segmentation, appointment outcomes, and operational insights.
  • Contribute through Git feature branches, local development, AI-assisted coding, debugging, product testing, and privacy-aware data handling.

AI & Innovation Intern

Compass Pro Bono

  • Built an AI-powered grant intelligence workflow integrating six tools across search, extraction, LLM analysis, Google Sheets, automation, and Slack.
  • Designed 10 targeted search strategies and a 14-field evaluation framework for relevance, deadlines, funding fit, and recommended actions.
  • Automated a twice-weekly search → analyze → store → share pipeline supporting nonprofit AI adoption and capacity building.

Teaching Assistant

University of Maryland

  • Develop applied AI research projects involving LangGraph, RAG, Graph-RAG, knowledge graphs, vector databases, SQL systems, APIs, and evaluation.
  • Built multi-tool systems for SEC financial intelligence and multi-tier supply-chain risk reasoning using ChromaDB, SQL Server, Neo4j, and OpenAI.
  • Create technical documentation and examples covering LangChain, tool calling, structured outputs, streaming, retrieval, and agent orchestration.

Graduate Industry Practicum Consultant — AI Systems

University of Maryland · Microsoft industry client

  • Collaborate on an AI-powered multi-agent concept for emergency medical services, focused on patient intake, routing, handoffs, and coordination.
  • Translate stakeholder needs into workflows, architecture, data models, and an implementation roadmap using Microsoft ecosystem tools.
  • Work within a five-member consulting team on a synthetic-data, privacy-conscious prototype and measurable workflow targets.

Cloud Engineer

Jio Platforms Ltd.

  • Supported enterprise Linux and cloud infrastructure while resolving operating-system, VM, and production issues through incident workflows.
  • Performed patching and infrastructure operations across 50+ servers while contributing to VM migration, resizing, automation, and reliability.
  • Collaborated with engineering teams and Red Hat support to help maintain a 99.9% infrastructure uptime target.

03 · Selected work

Projects designed around real failure modes—not just demos.

View all on GitHub
01

Reliable multi-tool financial AI

Agentic RAG for Financial Intelligence

A LangGraph system that routes SEC filing questions to semantic retrieval, structured SQL analysis, live EDGAR search, or a combined workflow—then validates numeric answers before returning them.

100% routing accuracy across 19 evaluation questions
LangGraphOpenAIChromaDBSQL ServerSEC EDGAR
Case study
02

Multi-hop reasoning over complex dependencies

SupplyGraph: Graph-RAG for Supply Chain Risk

A hybrid agent that combines Neo4j graph traversal with semantic search to trace how supplier disruptions propagate across tiers and affect finished products.

90% overall hybrid-agent accuracy
LangGraphNeo4jGraph-RAGText-to-CypherVector Search
Case study
03

Amazon Rufus-inspired product assistant

AI Shopping Agent

A conversational shopping assistant that uses LLM tool calling to search products, inspect ratings and reviews, recommend options, and support shopping actions through a Streamlit interface.

End-to-end tool-calling workflow with a persistent product data layer
LangChainOpenAIStreamlitSQLitePython
Case study
04

Agentic workflow for food rescue

FoodBridge AI

An intelligent food-rescue workflow that matches surplus food with shelters, coordinates approvals, and automates communication while keeping a human in the loop.

Built for the UMD Agentic AI Competition
n8nSlackGoogle SheetsGmailLLM Workflows
Case study

04 · Toolkit

A broad technical foundation, organized around what I can build with it.

01

AI & Machine Learning

PythonLangChainLangGraphRAGGraph-RAGOpenAIScikit-learnEmbeddingsTool Calling

02

Data Engineering & Database

SQLSQL ServerNeo4jChromaDBGCPETLREST APIsData ModelingBigQuery

03

Software & Applications

TypeScriptJavaScriptStreamlitFastAPIGitGitHubVS CodeNext.js

04

Analytics & Automation

PandasNumPyMatplotlibTableauPower BIn8nCopilot StudioDataverseZapierGoogle SheetsSlack

05 · Contact

Have a data problem, an AI product idea, or a role where we can build something meaningful?

Let’s connect. I’m currently exploring full-time opportunities in Data Science, AI/ML Engineering, Applied AI, and Data Engineering.

Connect on LinkedIn Explore GitHub Email Me