Full Stack Developer| n8n | Framer| Kajabee| Webflow Expert
1x
Hired
53
Followers
Full Stack Developer| n8n | Framer| Kajabee| Webflow Expert
AI-Powered Finance & Market Intelligence Dashboard
I built a multi-tab interactive finance dashboard powered by Groq's LLM and Phi Agent framework, designed to help investors, analysts, and tech-savvy users gain real-time market insights and AI-powered financial research. This application combines AI-driven conversational capabilities with real-time data extraction from trusted financial APIs and web sources.
1
168
AI-Powered News Research Tool | Streamlit Web App
This project is a fully functional AI-driven news analysis tool built using Streamlit, designed to help users extract valuable insights from online news articles.
Key Features:
Accepts a news article URL as input
Uses Google Generative AI to analyze and understand the content
Splits and processes large articles using Recursive Text Splitting
Embeds content using Google Embedding Models
Indexes data with FAISS for efficient semantic search
Allows users to ask natural language questions, returning accurate answers along with cited sources
1
142
🚬 New Project: Migratory Story
Excited to kick off a new Shopify project for Migratory Story, a premium cigar store.
Services: Shopify setup, UI/UX design, Figma prototypes, ecommerce management, and sales-driven content.
#Shopify #Ecommerce #PremiumCigars #UIUXDesign #Figma #DirectResponseMarketing
1
234
Human Resource Intelligence Chatbot with SQL-Driven Data Visualization
I developed an AI-powered HR chatbot that transforms natural language queries into actionable insights through SQL-driven analytics and automated visualizations.
How It Works:
HR asks questions in plain English
AI generates/executes SQL queries
Processes workforce data
Outputs structured results or charts
Key Features:
Natural language to SQL conversion
Real-time workforce analytics
Automated data visualization
Scalable integration with HR databases
Extendable to other chart types
FinTech developer building secure, modern web platforms.
New to Contra
FinTech developer building secure, modern web platforms.
Overview
This project provides an interactive platform for financial data analysis and predictive modeling. Built with Python and Streamlit, it enables users to visualize financial trends and explore machine learning-driven insights through an intuitive, web-based interface.
Key Features
Data Pipeline: Automated ingestion and cleaning of financial datasets.
Feature Engineering: Implementation of financial indicators and technical features to capture market dynamics.
Predictive Modeling: A streamlined training and evaluation workflow using robust machine learning algorithms.
Interactive Visualization: Real-time dashboards allowing users to experiment with different parameters and model configurations.
Technical Workflow
Data Loading: Robust ingestion of historical financial data.
Preprocessing: Handling missing values, noise reduction, and data normalization.
Feature Engineering: Extraction of meaningful market features (e.g., technical indicators, volatility metrics).
Model Training & Evaluation: A modular approach to training, testing, and validating model performance using industry-standard metrics.
Experience It Live
Explore the application and interact with the model here:
👉 Financial ML Dashboard (https://vtt4xouy7ifekdm7s5c4zj.streamlit.app/)
0
132
Project Name: Pakistan Street Food Guide
Project Overview
Designed and developed a multi-page, custom website celebrating the rich culinary heritage and vibrant street food culture of Pakistan. The "Pakistan Street Food Guide" serves as a digital exploration of traditional recipes, local favorites, and the stories behind regional street food vendors.
Key Features & Deliverables
Custom Multi-Page Architecture: Structured a seamless navigation experience across dedicated sections, including the homepage, a visual Food Gallery, and a Contact portal.
Lightweight Front-End Engineering: Built entirely from scratch using clean HTML5, CSS3, and vanilla JavaScript. By avoiding heavy external frameworks, the site maintains rapid load times and a highly optimized codebase.
Semantic UI/UX Design: Developed an intuitive, image-focused layout designed to highlight cultural storytelling and visual content effectively across different screen sizes.
#html #CSS#Frontend #javascript#webdevelopment
0
111
Project Title: Privacy-Preserving Sepsis Prediction Model
Role: AI Research Intern
The Challenge:
Integrating complex Recurrent Neural Network (RNN) architectures within a privacy-preserving Multi-Party Computation (MPC) environment.
Addressing the "fixed-point arithmetic" limitations inherent in cryptographic frameworks when handling 48-hour sequential medical data.
My Approach:
Mentored by a Yale University researcher to bridge the gap between AI and secure cryptographic protocols.
Independently engineered custom normalization and clipping techniques to resolve data overflow issues caused by sequential computation loops.
Successfully optimized the model for the MIMIC-III dataset, ensuring high-quality, functional code performance.
The Outcome:
Successfully contributed the finalized research implementation to the official open-source repository.
Demonstrated technical maturity in handling complex engineering bottlenecks while adhering to formal research methodologies.
Here is my repo link: https://github.com/sum710/sequre
0
126
Title: Civitas: Digitizing Community Savings & Financial Trust with AI
Description:
Traditional community-based saving groups (committees/ROSCA) have always been built on trust, but they often struggle with manual record-keeping, transparency issues, and security risks.
I am excited to share Civitas, a full-stack FinTech solution designed to modernize the committee system. Civitas transforms how communities save and contribute money by blending automated financial management with AI-driven security.
Key Features:
Digital ROSCA Management: A transparent platform where users can join, track, and manage their committee contributions automatically.
AI-Powered Trust Engine: A scoring logic that tracks payment consistency and user reliability, ensuring a safe ecosystem.
Payout Security: Payouts are protected with mandatory Two-Factor Authentication (2FA) and Google OAuth integration.
Modern Tech Stack: Built with React 19, Supabase Cloud, and AI financial advisors.
Why Civitas?
In the world of FinTech, trust is everything. Civitas replaces paper-based tracking with a permanent, automated digital ledger, reducing human error and building a stronger, more reliable financial community.
Explore the live project here: https://civitas-backend.vercel.app/
I’d love to hear your thoughts on how digital transformation is changing the landscape of community-based finance!
#FinTech #WebDevelopment #FullStack #AI #ProductDesign #Civitas #FinancialInclusion
Just wrapped up my Autonomous Resume Verifier for the Micro1 Challenge! I built this AI agent to automate candidate screening by parsing and evaluating resumes instantly.
Tech Stack: Python, Streamlit, Llama 3 & Groq API.
Check out the video to see it in action! Let me know what you think.
#ArtificialIntelligence #Python #Streamlit #Llama3 #Groq #Micro1Challenge #WebDevelopment #AIAgent #FreelanceDeveloper
3
3
688
Autonomous AI Agent Resume & Portfolio Verifier
An autonomous, multi-agent verification engine built for the Micro1 Frontier Engineering Challenge.
While standard single-prompt LLMs often miss subtle discrepancies in candidate resumes, this AI agent utilizes a multi-step tool-calling workflow to deeply verify candidate claims, cross-reference job constraints, and track execution trajectories in real time.
Key Highlights:
Agentic vs. Baseline Comparison: Live side-by-side verification showing how agentic reasoning outperforms standard LLM prompts.
Deep Tool-Calling Trajectory: Up to 10-step execution depth with transparent reasoning logs.
Discrepancy Detection: Automated identification of missing job titles, mismatched experience, and unverified credentials.
Tech Stack:
Python | Streamlit | Groq API (Llama 3) | Multi-Agent Architecture | Tool-Calling Workflows
0
178
Nova Mart - AI-Powered E-Commerce Assistant & Smart Chatbot
A modern full-stack e-commerce web application integrated with an intelligent AI shopping assistant built using Next.js, React, Node.js, and Groq.
1
293
Built a modern, high-performance agency website using Next.js, React, and Tailwind CSS. Fully responsive with a clean UI and lightning-fast speed.
CS student & designer automating the future with AI.
CS student & designer automating the future with AI.
Taking corporate email automation beyond basic template generation. 🚀
I just open-sourced a new project: Autonomous Cold Email & Inbound Replier Agent! This is a modular, production-ready system built completely in pure Python using CrewAI for multi-agent orchestration and Streamlit for a clean, modern interactive UI.
As shown in image_ea414f.png, the system moves away from single-prompt generation and splits the operational workload into specialized, sequential steps to ensure high-quality enterprise triage:
Dynamic Context Parsing: Ingests dynamic company names, specific roles, and product offerings to craft completely personalized pitch assets based on an internal knowledge base.
Multi-Agent Orchestration: Uses a CrewAI sequential flow to separate analysis from execution. A Triage Officer handles data categorization while a Business Correspondent handles context-aware drafting.
100% Free-Tier & Cost Compliance: Powered entirely by high-performance models via free-tier API orchestration (utilizing gemini-2.5-flash via Google AI Studio and Groq Cloud AI as a high-speed secondary model).
Interactive UI Safety: Features a polished Streamlit interface (onee.py (http://onee.py)) to monitor active server queues and act as a human-in-the-loop gatekeeper to approve drafts before they go live.
The repository is modularly structured, completely production-ready, and optimized with strict exception handling to respect rate limits safely.
🔗 Check out the code here: https://github.com/26FajarRizwan/Cold_Email_Replier_Agent
#CrewAI #Streamlit #AIEngineering #Python #GenerativeAI #LLMs #OpenSource #Automation #GoogleGemini
0
63
🎮 Level Up: Built a Multi-Agent AI Game Designer with CrewAI (https://www.linkedin.com/company/getcrewai/) & Groq (https://www.linkedin.com/company/groq/)! 🚀
I'm thrilled to share my latest projecta modular hashtag#AI (https://www.linkedin.com/search/results/all/?keywords=%23ai&origin=HASH_TAG_FROM_FEED) Agent system designed to transform a simple text idea into a full, production-ready Game Design Document (GDD)! 🕹️🤖
As game development gets more complex, brainstorming core mechanics, balance, and narrative loops manually can take days. I built this automation agent to instantly structure wild game ideas into comprehensive design blueprints.
🛠️ How It Works:
Dynamic Terminal Prompting: Captures unique, raw gameplay ideas directly from user input via the terminal.
AI Game Designer Agent: Powered by Groq’s lightning-fast Llama-3.3-70b-versatile model, it acts as a veteran designer with 10+ years of AAA experience.
Custom Stability Patch: Implemented a robust dynamic litellm execution patch to strip out incompatible caching fields, ensuring 100% crash-free API calls.
Structured GDD Output: Automatically generates core gameplay loops, combat systems, character arcs, and world-building documentation.
🏗️ Modular Architecture & Tech Stack:
Framework: CrewAI (https://www.linkedin.com/company/crewai-inc/) (Multi-Agent Architecture)
Inference Engine: Groq (https://www.linkedin.com/company/groq/) API Cloud
LLM: Llama (https://www.linkedin.com/company/ai-deepseek/)-3.3-70b-versatile
Environment Management: Python (https://www.linkedin.com/company/learn-python-programming/) hashtag#python (https://www.linkedin.com/search/results/all/?keywords=%23python&origin=HASH_TAG_FROM_FEED)-hashtag#dotenv (https://www.linkedin.com/search/results/all/?keywords=%23dotenv&origin=HASH_TAG_FROM_FEED) & hashtag#strict (https://www.linkedin.com/search/results/all/?keywords=%23strict&origin=HASH_TAG_FROM_FEED) .hashtag#gitignore (https://www.linkedin.com/search/results/all/?keywords=%23gitignore&origin=HASH_TAG_FROM_FEED) protocol to ensure zero leakage of private hashtag#API (https://www.linkedin.com/search/results/all/?keywords=%23api&origin=HASH_TAG_FROM_FEED) credentials.
By separating my automation projects into clean, isolated ecosystems, I'm building a highly scalable portfolio of production-grade AI tools.
📂 Check out the GitHub Repository here: https://lnkd.in/dFecvgBc
(https://lnkd.in/dFecvgBc)What kind of game would you ask this agent to design first? Let's connect and discuss the power of fast inference in creative automation! 👇
hashtag#AI (https://www.linkedin.com/search/results/all/?keywords=%23ai&origin=HASH_TAG_FROM_FEED) hashtag#GenerativeAI (https://www.linkedin.com/search/results/all/?keywords=%23generativeai&origin=HASH_TAG_FROM_FEED) hashtag#CrewAI (https://www.linkedin.com/search/results/all/?keywords=%23crewai&origin=HASH_TAG_FROM_FEED) hashtag#Groq (https://www.linkedin.com/search/results/all/?keywords=%23groq&origin=HASH_TAG_FROM_FEED) hashtag#Llama3 (https://www.linkedin.com/search/results/all/?keywords=%23llama3&origin=HASH_TAG_FROM_FEED) hashtag#GameDesign (https://www.linkedin.com/search/results/all/?keywords=%23gamedesign&origin=HASH_TAG_FROM_FEED) hashtag#Python (https://www.linkedin.com/search/results/all/?keywords=%23python&origin=HASH_TAG_FROM_FEED) hashtag#Automation (https://www.linkedin.com/search/results/all/?keywords=%23automation&origin=HASH_TAG_FROM_FEED) hashtag#ArtificialIntelligence (https://www.linkedin.com/search/results/all/?keywords=%23artificialintelligence&origin=HASH_TAG_FROM_FEED) hashtag#SoftwareEngineering (https://www.linkedin.com/search/results/all/?keywords=%23softwareengineering&origin=HASH_TAG_FROM_FEED)
0
68
Just Built: A Multi-Agent AI CV/Resume Tailor using CrewAI & Google Gemini 2.5 Flash! 📝
Huge thanks to Skill2Success for giving me this platform and helping me in making these type of projects and also Zarmina Sanam for guiding me in best way!!!!
Job hunting is tough, but tailoring your resume for every single job description shouldn't take hours. To solve this real-world problem, I built an automated multi-agent system that optimizes resumes for ATS algorithms in seconds!
🛠️ How it works:
Local PDF Extraction: Uses pypdf to read the candidate's resume directly via file paths (supporting drag-and-drop inputs).
ATS Specialist Agent: Analyzes the target Job Description (JD), evaluates keyword density, and flags technical or formatting gaps.
Executive Resume Writer Agent: Automatically re-architects and rewrites resume bullet points using the impact-driven STAR methodology without fabricating skills.
🏗️ Tech Stack:
Orchestration: CrewAI Framework
LLM Backbone: Google Gemini 2.5 Flash (Ultra-fast & accurate processing)
Security: strict .gitignore configuration to safeguard personal API credentials.
This project isolates production environment workflows perfectly and delivers tailored markdown resumes ready for corporate submissions!
📂 Check out the GitHub Repository here: https://lnkd.in/dvT4BK2S
Let's connect and discuss building autonomous agents for productivity workflows! 👇
1
93
rule-based chatbot built in Python that replies to greetings, questions, and casual conversation using keyword matching — no AI/ML involved. Includes an advanced version with jokes, time/date, and emotion responses, plus a bonus HTML/CSS/JS chat UI. CodeAlpha Python Internship Task 4.