Worked on an RLHF (Reinforcement Learning from Human Feedback) pipeline focused on dataset creation, data annotation, and model evaluation. My role involved designing and curating high-quality prompt datasets, reviewing AI-generated responses, and providing structured feedback based on accuracy, relevance, safety, and helpfulness. Contributed to improving model performance by ensuring consistent evaluation standards and high-quality human feedback for training alignment and refinement.
1
181
Retail Knowledge Graph
In this project, we built a semantic knowledge graph tailored to the retail industry. The pipeline involved developing AI agents to transform heterogeneous data into standardized formats. Ontologies were created to represent domain knowledge accurately. Using Gemini models and LangChain, user queries were converted into Cypher queries to retrieve insights from a Neo4j database. We utilized an MCP server for orchestration and LangSmith for secure login and audit trails. This system enhances complex data exploration for non-technical users.
2
2
208
Student Medical Chatbot
Built a chatbot to assist MBBS students in navigating medical literature. Leveraged Llama Index and fine-tuned language models to ensure accuracy. Embeddings were stored in OpenSearch, hosted on AWS. The Django backend included secure authentication and session management for a robust user experience.
0
110
Prompt Engineering Mini-Academy is a digital learning product built using Kajabi. It helps users learn how to write better AI prompts and use AI tools for daily tasks such as writing, research, summarization, and productivity.
The problem it solves is that many people use AI tools without a proper structure, which leads to weak or generic results. This product gives users a clear learning path, practical prompt templates, and workflow examples to improve the quality of their AI outputs.
I used Kajabi to create the landing page, email capture form, downloadable prompt resource, product offer, checkout page, and course structure. A sample video is attached to demonstrate the product flow and user experience.
An anomaly detection system for EV battery telemetry data using machine learning. The project identifies abnormal patterns in battery data to support early fault detection and predictive maintenance.
0
33
An end-to-end OCR pipeline combining YOLOv11s for real-time document region detection with EasyOCR for multilingual text extraction from scanned documents and images.
0
26
A real-time multi-object detection and tracking system built with YOLOv8. It detects objects in video streams and assigns persistent IDs across frames, enabling real-time tracking for surveillance and motion analysis.
0
33
A face recognition system that identifies and verifies individuals from images and live video streams using deep learning-based facial embeddings and similarity matching.
AI Engineer & Creative Strategist create Immersive Solutions
9
Followers
AI Engineer & Creative Strategist create Immersive Solutions
Diabetes Prediction System
Developed a prediction system using Pima Indians dataset, achieving 84% accuracy with Random Forest. Performed comprehensive data cleaning and median imputation for missing values. Implemented feature scaling and model evaluation with cross-validation.
84% Accuracy Data Cleaning Feature Scaling
Technologies
Python Scikit-learn Pandas Random Forest
1
130
Zuha Junaid - 3D AI & Software Engineer Portfolio
A modern, immersive 3D portfolio website showcasing AI/ML projects, full-stack development expertise, and technical skills. Built with cutting-edge web technologies and designed with glassmorphism aesthetics.
🌐 Live Portfolio: https://zuha3dport-s3994me9.manus.space
✨ Features
🎨 Design & Aesthetics
Dark Glassmorphism: Frosted glass cards with backdrop blur effects
3D Animations: Animated particle background with mouse interaction
Responsive Design: Fully optimized for desktop, tablet, and mobile devices
Smooth Transitions: Elegant page transitions and hover effects
Premium Color Palette: Dark blue (#0a0e27) with teal (#1dd1a1) and purple (#a29bfe) accents
📄 4 Complete Pages
Home - Hero section with animated 3D background and quick stats
About - Technical skills showcase, education, and interests
Projects - 4 major projects with detailed descriptions and technologies
Contact - Contact form and social media links
🎯 Interactive Elements
Animated particle background system
Glass card hover effects
Staggered entrance animations
Smooth page navigation
Responsive contact form
Social media integration
1
54
Executive Summary
The primary objective of this project was to identify and mitigate security vulnerabilities within a custom-built academic portal. By implementing a defense-in-depth strategy, the assessment utilized multiple security testing methodologies to ensure a robust security posture. The evaluation revealed moderate security risks, primarily involving server misconfigurations and missing security headers.
2
195
Al-Insaan Care: A Supportive App for Illiterate Needy People
Al-Insaan Care is a mobile application specifically designed to bridge the accessibility gap for illiterate and needy individuals. By removing traditional text-based barriers, the platform empowers users to request and receive essential financial aid and material donations—including food, clothing, electronics, and blood—with dignity and ease.
Project Overview
The primary goal of Al-Insaan Care is to provide an inclusive, user-friendly experience for populations that struggle with literacy. The application leverages multimedia tools to ensure that navigating the path to assistance is as intuitive as possible.
Key Features
Accessibility-First Design: Information is presented through visuals, audio instructions, and videos rather than text.
Voice-Activated Requests: Users can submit vital information (CNIC, address, house details) via voice messages or direct calls.
Thorough Verification: An administrative department validates all requests to ensure aid reaches those truly in need.
Streamlined Distribution: Integrated delivery services handle the distribution of material goods, while money and blood are managed through direct channels.
Social & Community Engagement: A social feed allows for community interaction and updates on humanitarian efforts.
UI & User Experience
The interface is designed to be clean and minimalist, focusing on high-contrast iconography and simple workflows.
Main Components
Section AND Description
Donation Portal: Uses icons (cutlery for food, shirt for clothing, etc.) to help users identify categories without reading.
Checkout Flow: A simple process with a 100% discount model for needy recipients, resulting in a total cost of Rs.0.
Dashboard: Provides administrators and donors with a visual overview of contributions and user growth through line graphs.
Chat Interface: Includes a microphone option for instant voice commands and communication with support staff.
Activity Feed: Tracks real-time user interactions, likes, and comments to foster a supportive community.
How It Works
Request: A user in need accesses the app and submits their details using voice commands or multimedia tools.
Verify: The administrative team reviews the voice-submitted data and validates the request.
Fulfill: Donors or the organization provide the requested items.
Deliver: The delivery department ensures the items reach the verified address via courier or direct distribution.