Skip to content
View ShainaHussain's full-sized avatar
🎯
Focusing
🎯
Focusing
5 followers · 2 following

Achievements

Achievement: YOLO

Achievements

Achievement: YOLO

Block or report ShainaHussain

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
ShainaHussain/README.md

👋 Hello, I'm Shaina

AI Systems Engineer • ML Researcher • Backend Developer

I enjoy building AI systems that go beyond prompt engineering—designing reliable pipelines, efficient retrieval systems, agentic workflows, and practical machine learning applications.

🚀 Currently

  • 🔬 Research Intern @ NIT Kurukshetra
  • ⚙ AI Engineer @ Unizoy
  • 🌱 GSSoC 2026 Contributor
  • 💻 200+ LeetCode Problems

❤️ Interests

  • Agentic AI
  • Retrieval-Augmented Generation
  • FastAPI
  • NLP Research
  • AI Infrastructure
  • Backend Systems
Experience Research Projects CGPA
2 NLP 3 Featured 8.43

⚡ Featured Work

Instead of building applications around LLMs, I enjoy engineering the systems that make them faster, cheaper, and more reliable.


# 🚀 Featured Projects

🎙️ Meeting Intelligence



End-to-end meeting assistant that converts speech into structured summaries with speaker-aware transcription.

⚙ Stack

Whisper

AssemblyAI

BERT

FastAPI

Streamlit

✨ Features

  • 🎤 Live Transcription
  • 👥 Speaker Identification
  • 📝 AI Summaries
  • ⚡ FastAPI Backend

😊 SentiMart



BERT-powered sentiment analysis platform for product reviews with an interactive prediction interface.

⚙ Stack

Python

BERT

PyTorch

Streamlit

✨ Features

  • 💬 Sentiment Prediction
  • 📊 Confidence Scores
  • ⚡ Live Inference
  • 🧠 Fine-tuned BERT

🛡️ Sentinel IDS



Machine Learning based intrusion detection system capable of identifying malicious network activity.

⚙ Stack

Random Forest

Flask

Next.js

Python

✨ Features

  • 🌐 Threat Detection
  • 📈 Live Dashboard
  • 🔐 REST API
  • 📊 NSL-KDD Dataset

💼 Experience

🔬 Research Intern

NIT Kurukshetra

Jun 2026 — Present

Working on improving the robustness of fake news detection models against cross-generator style attacks.

Highlights

  • Cross-generator robustness evaluation
  • LLaMA-based adversarial attacks
  • Generator-invariant representations
  • Legacy research code modernization

⚙️ AI Engineer Intern

Unizoy

Apr 2026 — May 2026

Built production-oriented AI systems with an emphasis on reducing compute cost and improving efficiency.

Highlights

  • Reduced LLM usage by ~60%
  • Intelligent document parsing
  • SQL Tool Calling Agent
  • Production RAG pipelines

🔬 Research Spotlight

GA-SheepDog

Generator-Adversarial Training for Cross-Generator Robust Fake News Detection

Current Focus

● Fake News Detection
● Adversarial NLP
● Domain Generalization
● Robust Representation Learning
● Style Attack Defense

🛠 Tech Stack

Languages & Frameworks



AI / Machine Learning

🌐 Let's Connect

⭐ If you like my work, consider following my journey.

Pinned Loading

  1. Amazon_Review_Analyzer Amazon_Review_Analyzer Public

    🛍️ SentiMart BERT-powered sentiment analysis system for Amazon product reviews with interactive dashboard and real-time processing capabilities achieving 90%+ accuracy. Tech Stack: Python • PyTorch…

    Python 1

  2. Meeting-Intelligence-System Meeting-Intelligence-System Public

    AI-powered meeting assistant that automatically transcribes recordings, extracts action items, identifies speakers, and provides sentiment analysis - deployed as a production-ready API.

    Python 1

  3. Sentinel-network-anomaly-detection-using-ML Sentinel-network-anomaly-detection-using-ML Public

    This project focuses on developing a machine learning-based system to detect unusual patterns or suspicious activities within a network that may indicate potential security threats. The system anal…

    TypeScript