Revati Natu

AI Researcher · Builder · Forever Learner

You found me. ✦

Behind the papers and the projects is someone who learns guitar badly, makes art with whatever's lying around, and goes down rabbit holes at 2am just because something was interesting.

If you're here, you're probably the kind of person I'd love to work with.
Get in touch at revatisnatu@gmail.comand let's build something cool together.

AI Researcher · Forever Learner · Builder · Occasional Artist

Revati Natu

I build things that learn. Researcher, builder, and sometime artist — currently deep in AI, NLP, and whatever rabbit hole opened up last night. When I'm not training models or reading papers, I'm making art with whatever's lying around, getting lost in a good book, or playing whatever I feel like on guitar — hard or not.

Scroll to explore
4+
Research Studies carried out
5+
Projects Shipped
2+
Years Building Cool Stuff
Computer Vision NLP Deep Learning LLMs RAG Systems Gen AI Machine Learning
PythonPyTorch TensorFlowHuggingFace LangChainComputer Vision NLPLLM Fine-tuning RAGGenerative AI Deep LearningResearch PythonPyTorch TensorFlowHuggingFace LangChainComputer Vision NLPLLM Fine-tuning RAGGenerative AI Deep LearningResearch

Multi-passionate builder

IT + AI Honours student at K J Somaiya School of Engineering, with a habit of going deep on everything I touch.

Research, code, art, music — I don't separate them. Depth over breadth, always. I write up everything I learn, build things to understand them better, and believe the best work happens at intersections.

Currently interning at Jio Creative Labs, working on AI content creation and internal tool development. Final year, finishing degree requirements in the next few months.

🔬
Research-first mindset Going beyond implementation to understand why things work — and publishing findings.
🎨
Mixed media artist Creating with whatever's around. Art and engineering share the same core: making something from nothing.
🎸
Guitarist (in progress) Learning music the same way I learn everything — slowly, deliberately, deeply.
📚
Compulsive reader & note-taker Rabbit holes are a feature. I write up everything — science, history, niche tech, whatever pulled me in.
🌏
Based in Mumbai, thinking globally Building a profile where opportunities come to find me.

Projects

Things I've made

Aug 2025
01

Automatic Data Analytics Tool

Interactive data analytics platform built and deployed on Streamlit — enabling real-time data exploration, visualisation, and insight generation through a clean, accessible interface.

PythonStreamlitData VizAnalytics
View Live →
May 2025
02

Research Paper Summarizer & Chatbot

Streamlit tool for uploading and querying research papers via Gemini Pro and LangChain — structured metadata extraction, CSV summarization, smart Q&A from PDFs.

Gemini ProLangChainStreamlitPython
Feb 2025
03

RAG System for Resume Analysis

Intelligent document analysis using RAG architecture — integrating LangChain, Ollama LLM, and vector embeddings for automated resume parsing and semantic search.

RAGLangChainOllamaVector DB
Apr 2025
04

ECG Arrhythmia Classification

Comparative analysis of ML and DL models for cardiac arrhythmia detection on the MIT-BIH dataset, evaluating tradeoffs in precision, recall, and generalisation across model families.

Random ForestDeep LearningMIT-BIHPython
Feb 2025
05

Forgery Detection via Inpainting

Computer vision system for image forgery detection using inpainting techniques on a large public dataset — deployed with a Streamlit interface for real-time inference with confidence scoring.

OpenCVCNNStreamlitPyTorch
2023–2024
06

Diabetes Prediction System

Linear Stacking Classifier built by evaluating 10+ ML algorithms with advanced preprocessing. Award-winning work, presented at an international conference.

scikit-learnStackingFeature Engineering

More on GitHub

Explore the full repository — including neural-engines (Karpathy series notebooks) and open source contributions.

5 research projects carried out across medical AI, NLP & computer vision

Research & Writing

Medical Imaging · IEEE

Multi-Cancer Classification via Deep Learning Techniques

Framework for multi-cancer detection across five cancer types using 65,000+ histopathology images. Evaluated DenseNet201 and Vision Transformer architectures with comparative analysis across multiple metrics and validation strategies.

DenseNet201 Vision Transformers TensorFlow Medical Imaging

NLP · Mental Health AI · IEEE

Depression Classification using Deep Learning Models

Hybrid LSTM–RNN architecture trained on the Sentiment140 dataset for depression signal classification from social media text. Explores sequential modelling for mental health NLP tasks with ablation analysis.

LSTM RNN NLP Sentiment140

🏆 Best Paper Award · Healthcare AI

Diabetes Prediction System

Linear Stacking Classifier built by evaluating 10+ ML algorithms with advanced preprocessing. Presented at an international conference — earned Best Paper award for innovative contributions.

Stacking Classifier scikit-learn Feature Engineering

Computer Vision · Conference

Image Forgery Detection via Inpainting

Computer vision system for forgery detection using inpainting techniques on a large public dataset. Deployed with a Streamlit interface for real-time inference with confidence scoring. Presented at an International Conference.

OpenCV CNN Streamlit Inpainting

Healthcare AI · Classification

ECG Arrhythmia Classification

Comparative analysis of ML and deep learning models for cardiac arrhythmia detection on the MIT-BIH dataset, evaluating tradeoffs in precision, recall, and generalisation across model families.

Random Forest Deep Learning MIT-BIH Python

Experience

Where I've built

Jan 2026 – Present

AI Intern

Jio Creative Labs · Reliance Jio · Mumbai

  • Working on a Combined Tools Website (React + Python) hosting six internal AI utilities including Manthan, Festive Calendar, Multiposter, BizIntel, Rembrandt, and Storyboard Generator.
  • Built a Live Sentiment Analysis Tool and contributed AI-generated content for client campaigns using Midjourney, Runway, Veo, Higgsfield, and Gemini.
Gen AI React Python LLMs Midjourney

Jan 2025 – May 2025

Software Development Engineer

Commonwealth Secretariat · Remote / International

  • Contributed to an AI prototype Early Warning Dashboard for the Governance & Peace Directorate — a tool designed to support conflict prevention across Commonwealth nations.
  • Worked at the intersection of AI, international governance, and real-world impact.
AI Prototype Dashboard Governance Tech International

Feb 2025 – Apr 2025

Deep Learning Intern

Forgery Detection System via Inpainting · Independent Research

  • Independently developed a computer vision system for forgery detection using image inpainting techniques on a large public dataset.
  • Built and deployed a Streamlit interface for real-time inference with confidence scoring.
  • Showcased at an International Conference.
Computer Vision Streamlit Conference Presentation

What I work with

A stack built around deep learning, NLP, and generative AI — with enough fullstack to ship things end-to-end. Hover to explore.

Languages

Python
C++
C
JavaScript
HTML/CSS
SQL

AI / ML Frameworks

PyTorch
TensorFlow
HuggingFace
LangChain
LangFlow
scikit-learn
OpenCV

Data & Tooling

Pandas
NumPy
Jupyter
Git / GitHub
Linux
Google Colab

Generative AI & Creative Tools

Midjourney
Runway
Veo
Gemini
Prompt Engineering
LLM Fine-tuning

Certifications

Generative AI with LLMs — DeepLearning.AI
Neural Networks & Deep Learning
Cybersecurity — Google

Achievements & Leadership

Beyond the code

🏆
Best Paper Award — International Conference
Diabetes Prediction System using Linear Stacking Classifier
Research Award
📄
IEEE Conference Paper Submissions (×2)
Multi-cancer classifier (99.93%) and depression classification model — under review
Publication
🌍
Commonwealth Secretariat Contribution
AI prototype for Early Warning Dashboard — Governance & Peace Directorate
International
🎓
9.4 CGPA — Honours in AI
K J Somaiya School of Engineering, Somaiya Vidyavihar University
Academic
👩‍🏫
Engineering Volunteer — Agastya International Foundation
Mentored school students in STEM (JPMC-funded program), Oct 2024–Feb 2025
Mentorship
🗣️
General Secretary — National Service Scheme (NSS)
Led 100+ member team, 5+ brainstorming sessions, community initiatives, SVU 2023
Leadership

Contact

Let's make something

Open to research collaborations, internship opportunities, full-time roles post-graduation, and interesting conversations. If you're building something meaningful, reach out.

Available for opportunities · Based in Mumbai, open to remote