Freelancers using GitHub in Punjab
Freelancers using GitHub in Punjab
Sign Up
Post a job
Sign Up
Log In
Filters
2
Projects
People
Umaima Iqbal
Lahore, Pakistan
I build offline AI tools that make documents talk.
New to Contra
Follow
Message
I build offline AI tools that make documents talk.
2
AuraExtract — Intelligent Invoice & Receipt Data Extractor The extraction engine uses intelligent regex pattern matching that handles real-world invoice layouts — column-per-line PDF formats, inline tabular formats, and plain text documents. It detects 10 fields automatically and parses up to 20 line items per invoice. Supports PDF, TXT, and DOCX formats. Includes a raw text preview panel so users can verify exactly what the engine is reading. CSV export includes both the summary fields and full line items table — ready to open directly in Excel. Pure Python. Zero external dependencies beyond pypdf for PDF reading.
2
150
2
AuraSort scans any folder and automatically sorts files into named subfolders by type — Documents, Images, Videos, Audio, Code, Archives, and more. Files are renamed to clean, consistent lowercase format. Every operation is logged live on screen as it happens. Built with a Dry Run mode so users can preview exactly what will move before anything is touched. Full undo restores every file to its original location with one click. An HTML report is generated after each sort showing every file moved, every category created, and total time taken. Pure Python. Zero external libraries. Works on any machine without installation.
2
154
1
A fully offline document summarizer built in pure Python. Uses TF-IDF scoring, position weighting, and Jaccard deduplication to extract the most important sentences from any PDF, DOCX, or TXT file — each labeled with a relevance percentage. The result looks like this: [1] [100% relevance] The algorithm achieved 94% accuracy on benchmark tests. [2] [81% relevance] Training was performed on 50,000 labeled samples. [3] [67% relevance] Results were validated using 5-fold cross validation. Supports PDF, Word, and TXT files. Saves summaries to your computer. Runs completely offline. No subscriptions, no API keys, no internet required.
1
146
1
Built AuraChat v3.0 — a fully offline Document Intelligence desktop app in pure Python. Users upload any PDF, Word, or TXT file and ask questions in plain English. The system returns cited answers with confidence scores instantly. Technical highlights: — Custom NLP engine using TF-IDF scoring + hybrid token overlap analysis — 1,700× faster indexing than baseline on 500-page documents — Multi-threaded processing — UI never freezes during heavy indexing — Supports PDF, DOCX, and TXT file formats — Zero external APIs — runs completely offline on the user's machine — 23 production-grade bugs identified and resolved before delivery This is not a demo. This is production-ready software built with clean architecture, full error handling, keyboard shortcuts, chat export, source citations, and confidence indicators
1
152
GitHub
(3)
Follow
Message
Abdul Razaq Ali
pro
Lahore, Pakistan
Website & Game developer and designer.
$5k+
Earned
3x
Hired
5.0
Rating
8
Followers
Follow
Message
Website & Game developer and designer.
1
BobaQuest PC & Mobile • Kickstarter A cozy adventure game for PC and a geolocation-based AR experience, blending a traditional PC adventure with real-world interaction on mobile. Built to appeal to a wide audience with a unique mix of adventure and cutting-edge Augmented Reality. Kickstarter = https://www.kickstarter.com/projects/bobaquest/boba-quest Learn more = https://bobaquest.com/
1
269
1
⏳ The Last Second — Unity 20th Anniversary Game Jam Winner Action Puzzle • PC / WebGL • Solo Dev • 48h Jam A fast-paced, time-bending action game created in just 36 hours and selected as a winner of the Unity 20th Anniversary Game Jam. Designed, developed, optimized, and polished solo — showcasing rapid prototyping, creativity, and strong execution under pressure. Devlog = https://www.youtube.com/playlist?list=PLMmCMMvt_NgVD0HVD3vD49fz3edKpaC3M Play demo = https://razzaq94.itch.io/the-last-second
1
296
2
Protectee Planner is an interactive 2D/3D room planning platform I developed to help users design, customize, and visualize spaces with an intuitive drag-and-drop experience. Built as a cross-platform web solution, it combines real-time 2D layouts with immersive 3D visualization, allowing users to create room designs, arrange furniture, and preview concepts before implementation. 🔹 Key Highlights: ✔️ 2D & 3D Design Engine – Developed a dual-mode planning system allowing users to seamlessly create floor layouts and explore realistic 3D environments. ✔️ Drag-and-Drop Furniture Editor – Built an interactive customization system for placing, moving, and managing furniture elements within rooms. ✔️ Real-Time Visualization – Enabled instant design previews with synchronized changes between 2D plans and 3D scenes. ✔️ Responsive Web Experience – Created a cross-device compatible application accessible across desktop, tablet, and mobile platforms. ✔️ Interactive Room Customization – Implemented tools for users to design spaces with flexibility and control without technical expertise. ✔️ Scalable 3D Architecture – Developed the foundation for expanding furniture libraries, assets, and advanced planning features. 🌟 Impact: Protectee Planner simplifies interior planning by combining professional-level visualization with an easy to use interface. The platform empowers users to experiment with layouts, visualize ideas in 3D, and make confident design decisions through an accessible digital planning experience.
1
2
135
0
Legitly AI is an AI-powered luxury authentication platform I developed to help users verify the authenticity of high value products including watches, sneakers, and designer items. The platform combines AI image analysis, intuitive mobile workflows, and smart verification systems to simplify counterfeit detection and provide users with confidence before making purchases. 🔹 Key Highlights: ✔️ AI Authentication Engine – Built an intelligent verification workflow that analyzes product images and identifies authenticity indicators. ✔️ Luxury Product Recognition – Designed support for multiple categories including watches, sneakers, and fashion accessories. ✔️ Smart Scanning System – Developed a guided image capture experience to collect the necessary product details for AI analysis. ✔️ Verification Dashboard – Created a clean interface for viewing scan results, history, and authentication outcomes. ✔️ Subscription & Usage Management – Integrated user plans, scan limits, and premium access features. ✔️ Modern Mobile UX – Designed a seamless dark-themed experience focused on simplicity, trust, and ease of use. 🌟 Impact: Legitly AI transforms luxury authentication by making counterfeit detection faster, more accessible, and technology-driven. By combining AI capabilities with a user-friendly mobile experience, the platform helps buyers, collectors, and resellers make safer purchasing decisions in the growing luxury marketplace.
0
99
GitHub
(2)
Follow
Message
Huzaifa Malik
Lahore, Pakistan
AI Software Engineer & Full stack developer
5.0
Rating
13
Followers
Follow
Message
AI Software Engineer & Full stack developer
0
https://pressline.unicorn-realtors.com/ pressline is here, what was an idea a day ago (which worked btw) is now on sale , mention everyone who you think can be a potential buyer so we can split the profit (yes refferal system is available).
0
8
1
Most AI blog generators write like a nervous intern trying to hit a word count. You ask for a market update and you get: "In today's ever-evolving fast-paced landscape, real estate is not just a trend, it is a testament to growth." Then it invents a tax rate that does not exist, gives you a payment table where the numbers add up to 130 percent, and gets immediately flagged as ninety percent AI by Google. I got tired of editing that garbage, so I built an autonomous 8-agent publishing engine instead. Here is what it actually does while I do other things: First, an AI researcher scans real search queries and market trends instead of regurgitating the same generic headlines. Second, an architect agent picks one of four distinct layouts so every article does not look like a cookie-cutter copy of the last one. Third, a writer agent drafts the piece strictly constrained by real prices, real tax brackets, and payment math that actually reconciles to one hundred percent. Fourth, a humanizer and critic loop strips out the robot cliches, balances sentence lengths, and blocks publication unless the AI detection score drops below fifteen percent. Finally, it generates an on-brand vector cover graphic, compiles the static HTML with full Schema data, and deploys it straight to the production server three times a day on a randomized schedule. Zero manual copy-pasting. Zero hallucinated numbers. Zero "in today's digital age." I am packaging this pipeline into a hands-free system for niche businesses and agencies who want daily organic search traffic without publishing robotic nonsense.
2
1
84
2
Zameen charges you to list your own plot. We thought that was a weird business model. Meet plottyy — a plot & property marketplace for Pakistan built around one idea: your listing, your leads, zero commission. OTP-verified listers, so no ghost listings or scraper bots. Native Marla, Kanal, and Sq. Yd support, with instant Lakh–Crore pricing. Click-to-reveal contact, so real buyers reach you directly. A free agency page with a shareable link and an auto-generated PDF brochure. Built for DHA, Bahria Town, Gulberg Greens, and every major Pakistani housing society. List a 5 Marla plot or run a full agency portfolio — plottyy gets it in front of real buyers, free. plotty.unicorn-realtors.com (http://plotty.unicorn-realtors.com) #RealEstatePakistan #PropertyListing #DHALahore #BahriaTown #PlotForSale #PropTech #PakistanRealEstate #exhuzaifa
2
45
1
I reviewed 200 losing Upwork proposals. Same 5 mistakes in almost all of them. Built a tool that catches them in 30 seconds. Free. pitchiq.zentisys.com (http://pitchiq.zentisys.com) Drop your proposal in the comments. I'll run it through and post your score publicly.
1
47
GitHub
(2)
Follow
Message
Adil Shahzad
pro
Lahore, Pakistan
Senior DevOps & DevSecOps Engineer · Cloud Security
Follow
Message
Senior DevOps & DevSecOps Engineer · Cloud Security
0
Enterprise DevSecOps platform and mobile delivery Reusable governed pipelines and automated store releases that cut a banking release cycle from weeks to days. Who it was for: A banking group with multiple product teams and a manual release process. The problem. Every team had built its own pipeline, releases were manual, and mobile submissions were a person following a checklist. Slow, and impossible to prove consistent to an auditor. What I did. Stood up the platform — enterprise CI/CD, artifact management and mobile security scanning — then built reusable pipeline templates with role-based access and policy enforcement so every team inherited the same controls. Automated mobile releases to both stores. Trained the engineering teams on the new path so it stuck after I left. The result. Release cycles moved from weeks to days, roughly 70% faster, with the same governance applied across every team by default.
0
16
0
Zero-downtime repository and pipeline migration Around 70 enterprise repositories moved to a new platform with history, policies and access intact. Who it was for: A large international organisation running enterprise development at scale. The problem. Source control and CI/CD had to move platforms without stopping delivery. Losing commit history, branch protection or access mappings would have been worse than not moving at all. What I did. Inventoried repositories and pipelines, then ran a staged cutover that preserved history, branch policies and access controls. Rebuilt pipelines on the target platform and wired in code scanning and quality gates on arrival, so the migration also raised the security baseline rather than just relocating it. The result. Roughly 70 repositories migrated with no delivery downtime, and automated vulnerability detection in place from day one on the new platform.
0
55
0
Driving SAMA CSF maturity from Level 2 to Level 3
0
0
0
Fraud and abuse detection wired into a SIEM Card-testing and brute-force detection routed to on-call with a runbook attached to every alert. Who it was for: A payments platform exposed to automated card-testing traffic. The problem. Automated enumeration against payment endpoints is both a fraud loss and an availability threat, and it doesn't announce itself. Without detection it looks like ordinary traffic until the chargebacks arrive. What I did. Built the log pipeline into the SIEM, then wrote detections for card-testing patterns, brute force and anomalous transaction behaviour. Tuned edge rate-limiting and bot controls to cut volume at the perimeter. Every alert routes to on-call with a runbook attached, so whoever is paged at 3am has the next step in front of them. The result. Repeat attempts are caught as they start rather than reconstructed afterward, and response is a documented procedure instead of improvisation.
0
42
GitHub
(2)
Follow
Message
Arslan Mehmood
Lahore, Pakistan
ML AI | Backend | Computer Vision | GenAI | LLM Agents
New to Contra
Follow
Message
ML AI | Backend | Computer Vision | GenAI | LLM Agents
2
LakeShield - AI-Powered Video Monitoring and Vessel Intelligence Platform I led the development of LakeShield as the Senior AI/ML Engineer and Lead Developer, taking the platform from initial research and experimentation to a scalable production system. My responsibilities included: 🔹 Designing the end-to-end AI and video-processing architecture 🔹 Building YOLO-based boat and vehicle detection pipelines 🔹 Developing object tracking and movement-analysis workflows 🔹 Implementing OCR for extracting boat registration information 🔹 Creating scalable pipelines for processing thousands of surveillance videos 🔹 Developing FastAPI backend services and automated data workflows 🔹 Building a Next.js analytics dashboard integrated with Supabase 🔹 Deploying and operating the AI pipeline on cloud GPU infrastructure 🔹 Optimizing model accuracy, inference speed, infrastructure costs, and reliability 🔹 Managing production monitoring, troubleshooting, maintenance, and continuous improvements The platform transforms raw surveillance footage into structured operational insights, enabling automated vessel monitoring, vehicle activity analysis, registration extraction, and reporting. This project involved complete technical ownership across Computer Vision, AI/ML, backend development, cloud infrastructure, data engineering, MLOps, and production operations. #ComputerVision #VideoAnalytics #ArtificialIntelligence #ObjectDetection #OCR #MLOps #FastAPI #NextJS #Supabase #CloudEngineering
2
101
2
Shelfr - AI-Powered Retail Shelf Intelligence Platform I led the development of Shelfr as the Senior Computer Vision Engineer and Lead Developer, taking the platform from the initial idea and system architecture through development, deployment, and production operations. My work included: 🔹 Designing the complete computer vision and backend architecture 🔹 Building product detection, shelf analysis, OCR, and image-processing pipelines 🔹 Developing APIs and scalable data-processing workflows 🔹 Deploying and managing production systems on GCP cloud servers 🔹 Optimizing model accuracy, processing speed, and infrastructure performance 🔹 Managing production monitoring, reliability, troubleshooting, and ongoing improvements 🔹 Leading technical decisions across AI, backend, cloud infrastructure, and DevOps The platform converts real-world retail shelf images into structured product and shelf-level insights, helping automate retail auditing, product visibility analysis, and inventory workflows. #ComputerVision #RetailAI #LeadDeveloper #AIEngineering #GCP #MLOps #Python #CloudEngineering
2
85
1
⚖️ Built a French Legal AI Assistant powered by advanced RAG and LLM technology. The system enables users to ask complex legal questions and receive accurate, context-aware answers grounded in French legal documents. Key features include: 🔹 Custom legal document ingestion and chunking 🔹 Metadata-based vector search 🔹 Hybrid retrieval and reranking 🔹 Agentic RAG workflows using LangGraph 🔹 Source-grounded answers with legal references 🔹 Private deployment on an Azure VM using locally hosted LLMs The main focus was improving retrieval accuracy, reducing hallucinations, and making large collections of legal documents easier to search and understand. #LegalAI #RAG #LLM #ArtificialIntelligence #LangGraph #Azure #GenerativeAI #MachineLearning
1
87
0
AI-Powered PDF Data Extraction My role: AI Data Processing and Extracton Engineer Organizations often struggle to extract structured and useful information from large volumes of unstructured PDF documents. I developed a flexible AI-powered data extraction solution that allows users to define the specific entities and fields they want to retrieve. The system processes different PDF formats, identifies relevant information, and converts it into structured, usable data. The solution reduces manual document processing, improves retrieval accuracy, and can be adapted to different document types and business requirements. A working demo link is attached.
0
76
GitHub
(1)
Follow
Message
Waseemullah Zahid
Rawalpindi, Pakistan
AI & Full-Stack Engineer turning ideas into intelligent appl
New to Contra
Follow
Message
AI & Full-Stack Engineer turning ideas into intelligent appl
0
Voicera AI – AI-Powered Voice Learning Platform Voicera AI is an intelligent educational platform that reimagines online learning through voice-first interactions. Inspired by Google Classroom but enhanced with conversational AI, Voicera enables students and educators to communicate naturally using voice, making learning more engaging, accessible, and interactive. Developed a full-stack AI-powered classroom platform with end-to-end voice integration. Enabled students to submit voice questions and receive AI-generated voice responses in real time. Integrated Speech-to-Text and Text-to-Speech technologies for seamless voice-based learning. Built AI tutoring capabilities that provide personalized explanations and instant academic support. Implemented classroom management, assignment tracking, announcements, and student progress monitoring. Designed for accessibility, allowing learners to interact with educational content through natural conversation rather than traditional text-based interfaces.
0
34
0
IntakeAI – AI-Powered Project Estimation & Workflow Analysis Platform IntakeAI is an intelligent project intake and estimation platform designed for automation agencies to streamline project scoping, workflow analysis, and pricing. The platform leverages AI to analyze complex n8n workflows, generate accurate cost estimates, and accelerate proposal creation while maintaining human oversight through a structured review process. Developed an AI-powered estimation engine that analyzes project requirements and n8n workflows to generate pricing and scope recommendations. Automated project intake, reducing manual effort in requirement analysis and proposal generation. Built a multi-user admin dashboard for review, approval, and collaboration across project stakeholders. Integrated MongoDB for scalable storage of projects, workflows, estimates, and review history. Implemented human-in-the-loop validation to ensure accuracy and quality before final client delivery. Streamlined workflow assessment and pricing operations, enabling faster turnaround times and improved estimation consistency.
0
24
0
ComparePro AI – AI Tool Discovery & Comparison Platform ComparePro AI is an intelligent platform that helps users discover, evaluate, and compare AI tools based on their specific needs. By understanding natural language queries, the platform recommends the most suitable AI solutions and provides detailed side-by-side comparisons to support faster decision-making. Built an AI-powered recommendation engine that suggests relevant AI tools from user queries. Developed intelligent matching algorithms to identify tools based on use case, features, pricing, and capabilities. Implemented side-by-side comparison functionality for informed tool selection. Enabled users to discover alternatives to popular AI products across multiple categories. Created a scalable database of AI tools with automated categorization and filtering. Designed a modern full-stack application focused on simplifying AI tool research and adoption
0
32
0
Shopify Theme Converter AI AI-powered platform that transforms existing websites into production-ready Shopify themes and templates. Automated website structure, styling, and component extraction for Shopify compatibility. Converts frontend layouts into reusable Shopify sections and Liquid templates. Reduces manual theme development time by generating Shopify-ready code with AI-assisted workflows. Supports rapid migration from custom websites to scalable e-commerce storefronts. For a more startup-style description: Built an AI-powered Shopify Theme Converter that analyzes any website and automatically generates a Shopify-compatible theme, enabling businesses to migrate to Shopify in minutes instead of weeks. 🚀
0
38
GitHub
(1)
Follow
Message
Khadija Subhani
Lahore, Pakistan
Backend & AI Engineer | Python, FastAPI, RAG Systems
New to Contra
Follow
Message
Backend & AI Engineer | Python, FastAPI, RAG Systems
0
AskRAG — RAG-Based Codebase Q&A Tool Built a retrieval-augmented generation (RAG) tool that lets developers ask natural-language questions about any codebase and get accurate, context-aware answers. Designed and built the full backend using FastAPI, with FAISS for vector storage and all-MiniLM-L6-v2 embeddings for semantic search. Integrated Gemini 2.5 Flash for response generation, PostgreSQL/Supabase for data persistence, and GitHub OAuth for secure repo access. Also built the React/Vite frontend and resolved a critical authentication bug involving JWT cookie handling. A working prototype demonstrating practical LLM application design — from embedding pipelines to secure auth flows. Project link: https://github.com/khadijayy/askrag
0
89
0
Social Engineering in Cyber Security - A RESEARCH PAPER
0
58
0
Adversarial Attacks on AI-Based Robotic Vision Systems - A REASEARCH PAPER
0
48
0
Synapse — AI-Powered Team Formation & Mentor-Matching Platform Built as a final year project — an AI-powered platform for team formation and mentor-matching, designed to help students and teams find the right collaborators using data-driven compatibility scoring. Built the Flutter frontend, the core matching engine (a seven-signal composite scoring system with a Random Forest collaboration predictor and SHAP-based explainability), the proximity module, and Firebase Cloud Messaging integration for real-time notifications. Also managed the deployment pipeline — backend on Render, frontend on Netlify. A fully deployed, functioning platform showcasing applied machine learning, mobile development, and real-time system design in one product.
0
59
GitHub
(1)
Follow
Message
Usama Mushtaq
Lahore, Pakistan
High-Performance Apps for Startups & Enterprise Clients
5.0
Rating
1
Followers
Follow
Message
High-Performance Apps for Startups & Enterprise Clients
0
Content Drafter is a web application designed to help users generate high-quality content using AI. It allows users to enter a text prompt and optionally upload an image, which are then processed through a backend pipeline that integrates multiple AI models. The system intelligently combines text and visual inputs to produce refined, context-aware content outputs. The frontend, built with Next.js, ensures a fast and responsive user experience, while the Python-powered backend handles AI orchestration, image processing, and model communication to deliver accurate and relevant results.
0
37
0
Afterlib is a powerful product research and competitor analysis tool, offering deep insights into ads, winning products, and top-performing creatives. Originally developed for internal use, it streamlines research and drives faster growth. I worked as a frontend developer on Afterlib, focusing on building a fast, user-friendly interface. The frontend is developed using React and Svelte for performance and flexibility.
0
52
0
Noshly is the ideal platform for hosting culinary pop-ups, providing chefs with the essential tools to manage successful events. As a senior backend engineer, I utilized Next.js, Node.js, and MongoDB to develop a robust and scalable solution. With Noshly, chefs can create and grow their concepts on their own terms, ensuring seamless experiences.
0
32
0
Stax is an innovative, AI-driven platform inspired by Scratch, designed to make game development accessible and engaging for users of all ages. By integrating artificial intelligence with a visual block-based coding interface, Stax empowers users to create interactive games and simulations without the need for traditional programming skills.
0
45
GitHub
(2)
Follow
Message
Explore people