I'm a third-year CSE student at GITAM University in Visakhapatnam (CGPA 9.17), interested in data engineering and backend work. I would rather build a pipeline that copes with bad input than tune a model for another half a point of accuracy.

• 💼 Software engineering intern @ Motherson Technology Services (AIML team). I built the chat-history storage for LegalLens, an AI legal-research platform: a FastAPI module with 9 endpoints, SQLite for metadata and Azure Blob Storage for message payloads.

I'm open to data engineering and backend internships.

B.Tech in Computer Science and Engineering · GITAM University, Visakhapatnam · 2024 to 2028

• 📚 Coursework: DBMS · Algorithms · Data Structures · Operating Systems · Data Warehousing and Mining · Computer Networks · Machine Learning · Probability and Statistics
• 📜 IBM Data Engineering Professional Certificate on Coursera: 16 courses across Airflow, Kafka, Spark, Hadoop, NoSQL and BI dashboards (see it on LinkedIn)

• 🔧 Started with C and C++, and I still care about memory and efficiency
• 🧱 Drawn to backends and data systems: APIs, ETL, schemas and anything that has to keep working when the input is messy
• 🚀 I like owning a thing end to end, from the database to the UI, and shipping it live
• 🔍 Fond of explainable results: SHAP reasons, audit logs and tests that say what broke

Project	What it does	Stack
	Two XGBoost classifiers trained on about 101,000 labeled accounts: 90.04% accuracy for X and 96.87% for Meta platforms. Removing a noisy tweet-level dataset lifted X from 67% to 90.04%. SHAP risk factors in plain English, a NetworkX graph for coordinated accounts, PDF case-file export, and Playwright scraping that never stores credentials. Built for SIH-1775 (ITBP / Ministry of Home Affairs).	Python, XGBoost, SHAP, FastAPI, React, NetworkX
	Scrapes market capitalization data for the largest banks, converts currencies with vectorized operations, and loads the result into SQLite and CSV, with timestamped logging at each stage.	Python, Pandas, NumPy, BeautifulSoup, SQLite
	Clinic app where students book doctors and doctors record diagnoses and prescriptions. Built at a 24-hour university hackathon; the repo has 29 integration checks.	Node.js, Express, PostgreSQL, JWT, bcrypt
	Road-trip planner with maps, nearby stops and a chat assistant. Started for Smart India Hackathon 2025, still in development.	TypeScript, React, Express, MongoDB, Gemini
	MERN app that connects kitchens with surplus food to NGOs.	MERN
	WebGL scene built from Spotify listening history.	WebGL
	Secure data erasure and file recovery tool with a hash-chained audit log.

Also, practice repositories I set up for first-time contributors at GITAM:

• 🏛️ President, IEEE Computer Society GITAM Vizag · Sept 2026 to now
• 🐙 Domain Lead, Open Source and Developer Experience (OS/DE), GitHub Community GITAM · Aug 2026 to now. I run Git and GitHub workshops and walk students through their first pull request
• ✈️ Aircraft Domain Lead, AeroGitam Club · Feb to Nov 2025

Languages

Data

Databases

Backend & Web

Machine Learning

Tools

Also: Make · GDB · Valgrind

• Smart India Hackathon 2026: internal-round qualifier, fake account detection engine (SIH-1775)
• Smart India Hackathon 2025: internal-round qualifier, TripSync
• 24-hour university hackathon: KAPS MedTech backend

• 🧩 Speed-cubing
• 🎶 Music, a lot of it. I even built a 3D map out of Spotify listening history (Orbitune)
• 📖 Books, mostly fiction
• 🍥 Anime, a lot of that too

_{The contribution graph and the snake are regenerated daily by the workflow in .github/workflows.}

I like building things.

📫 prsatyarthi2404@gmail.com · LinkedIn · Portfolio