Jaleed Ahmad
AI/ML Engineer integrating DevOps & Cloud.
New to Contra
Jaleed is ready for their next project!
Blizzup Agentic Bike Dealership
Project Overview
A sophisticated, full-stack AI-driven dealership platform that leverages Agentic AI to provide deep technical comparisons, transparent mathematical scoring, and automated inventory management. Built to fulfill a "Fullstack + AI Developer" assessment, the system uses a ReAct (Reason + Act) loop, allowing the AI to autonomously fetch real-world data and execute complex backend functions. (Note: The live AI agent functionality is currently disabled.)
Core Technologies & Frameworks
React, Tailwind CSS
Node.js, Express
Google Gemini AI (@google/generative-ai)
MongoDB Atlas / Mongoose
Pollinations.ai (http://Pollinations.ai) (Image Generation)
Key Features & Engineering Highlights
Agentic AI & Function Calling: Engineered a state-machine ReAct loop where the AI autonomously decides when to trigger real-time backend functions to retrieve inventory data, moving beyond traditional static prompting.
Explainable Scoring Engine: Developed a dynamic scoring system that evaluates bikes across five strict metrics (Price, Fuel Average, Engine Power, Value, Features), featuring "Thinking Accordions" that expose the AI's internal mathematical reasoning to the user.
Automated Bulk Ingestion: Built an intelligent pipeline allowing admins to ingest multiple vehicles by name; the AI automatically fetches exact technical specifications and generates high-fidelity photographic prompts.
Dynamic Image Generation & Self-Healing: Integrated Pollinations.ai (http://Pollinations.ai) to dynamically generate accurate vehicle images based on AI-classified categories (e.g., Mountain Bike vs. Superbike), alongside an automated admin utility to repair and refresh low-quality database thumbnails.
0
6
AI Image Forensics Web Application
Project Overview
A professional-grade, multimodal web application designed to detect and analyze AI-generated visual content. By combining traditional image processing techniques with advanced Large Vision-Language Models (VLMs), the platform provides comprehensive, automated analyses of image authenticity, digital signatures, and physical integrity.
Core Technologies & Frameworks
Next.js (React)
Python, FastAPI
Google Gemini Vision API
Docker, Google Cloud Run
Key Features & Engineering Highlights
8-Stage Forensic Pipeline: Engineered a highly robust image analysis pipeline that sequentially executes metadata scanning, quadrant tiling, Error Level Analysis (ELA), and Canny Edge detection.
Multimodal AI Analysis: Integrated Google Gemini Vision as an automated "forensic analyst" to evaluate visual inputs for physical inconsistencies, blending errors, and AI generation artifacts.
Decoupled Microservices Architecture: Built a high-performance Next.js frontend paired with a highly scalable Python/FastAPI backend to efficiently process complex mathematical image transformations.
Cloud-Native Deployment: Established automated workflows for containerizing the application with Docker and deploying the backend services to Google Cloud Run for scalable compute.
Data Visualization UI: Developed an intuitive, user-friendly dashboard to clearly present complex forensic findings, edge maps, and AI confidence scores to end-users.
0
10
AuraBeat: Context-Aware Music Curator
Project Overview
A full-stack, AI-driven application that generates highly personalized music soundscapes by blending real-time environmental data with deep user sentiment analysis. Built to seamlessly integrate advanced LLM decision-making with frontend aesthetics, the platform curates audio-visual experiences that map exactly to the user's current mood and local weather conditions.
Core Technologies & Frameworks
React 18, Tailwind CSS, Framer Motion
Node.js, Express.js
Google Gemini AI
YouTube Data API v3
Open-Meteo & Nominatim APIs
Key Features & Engineering Highlights
Context-Aware LLM Pipeline: Engineered an AI pipeline using Google Gemini to perform sentiment analysis on user input and merge it with real-time weather analytics for highly accurate, contextual song recommendations.
Dynamic UI & Color Theory: Built an ultra-responsive frontend featuring a dynamically shifting UI color palette that programmatically updates based on the AI's aesthetic evaluation of the recommended track.
Multi-API Orchestration: Seamlessly integrated multiple external APIs (YouTube, Open-Meteo, Nominatim) within an Express.js backend to stream official video content and fetch localized environmental data.
Decoupled Architecture: Designed a robust client-server architecture separating the Vite/React frontend from the Node.js backend, ensuring secure API key management and scalable request handling.
0
8
AI Study Notes Agent
Project Overview
A cloud-native, multi-user AI application designed to transform how users interact with and synthesize study materials. Built with a focus on end-to-end engineering and MLOps, this platform leverages advanced Retrieval-Augmented Generation (RAG) to deliver context-aware document analysis and automated study aids.
Core Technologies & Frameworks
Python, Streamlit
Google Gemini 2.5 Flash
LangChain, ChromaDB
Supabase (PostgreSQL)
gTTS (Google Text-to-Speech)
Key Features & Engineering Highlights
Intelligent Document Analysis: Engineered a robust RAG pipeline utilizing ChromaDB and LangChain to process documents and generate highly accurate, citation-backed insights.
1-Click Anki Flashcard Generator: Developed an automated pipeline that extracts key concepts from text and instantly formats them into Anki-ready flashcards for spaced-repetition learning.
Audio Podcast Conversion: Integrated gTTS to automatically convert study notes and summaries into audio formats, allowing users to consume educational content on the go.
Scalable Cloud Architecture: Designed a multi-user environment backed by Supabase PostgreSQL, utilizing UUIDs for secure, persistent data storage and user isolation.
LLM Output Formatting: Implemented strict prompt engineering and formatting harnesses to prevent LLM output drift, ensuring 100% reliable and seamless database insertions.
0
10