Freelancers using Python in Lahore

Freelancers using Python in LahoreFreelancers using Python in Lahore

Projects People

proLahore, Pakistan

AI Integration & Automation Engineer | Full-Stack Web Apps

$50k+: Earned

63x: Hired

4.9: Rating

101: Followers

Expert

Expert

+2

AI Integration & Automation Engineer | Full-Stack Web Apps

Cover image for Autonomous Multi-Agent Market Research System Development

Autonomous Multi-Agent Market Research System Development

2

9

Cover image for Magnai | UK Public Affairs

Magnai | UK Public Affairs

4

44

Cover image for Humoni - secure housing in under 72 hours

Humoni - secure housing in under 72 hours

3

93

Cover image for Wellbeing Wizard AI

Wellbeing Wizard AI

7

168

Lahore, Pakistan

AI/ML & Data Solutions Engineer

New to Contra

AI/ML & Data Solutions Engineer

Cover image for Developed a full-stack language learning

Developed a full-stack language learning application tailored for Luxembourgish, combining speech recognition, natural language understanding, and generative AI. Fine-tuned OpenAI’s Whisper model for accurate Luxembourgish transcription and built a custom text-to-speech (TTS) engine for realistic audio feedback. A RAG-based architecture enables the app to answer user queries contextually, making learning highly interactive. The frontend is built with React, while Flask powers the backend. Designed to deliver an immersive, conversation-driven auditory learning experience.

1

77

Cover image for Hey Contra!
Excited to finally

Hey Contra! Excited to finally be here and connect with builders, founders, and innovators from around the world. I'm Osman, an AI Engineer specializing in AI Agents, LLM Applications, Automation Systems, and Full-Stack Development. Over the past 3+ years, I've helped businesses transform ideas into intelligent products using OpenAI, Gemini, LangChain, LangGraph, FastAPI, Django, and modern cloud technologies. Some of the solutions I've built include: • AI Agents and Multi-Agent Systems • RAG Applications with Private Knowledge Bases • AI-Powered SaaS Products • Automation Workflows with n8n, Zapier, and Make • Voice AI Agents with Twilio and ElevenLabs • Custom Chatbots and Internal AI Tools • Data Automation and Web Scraping Systems I enjoy solving complex problems and building products that create real business value—not just demos. Looking forward to connecting with founders, startups, agencies, and teams working on exciting AI projects. If you're building something ambitious with AI, let's talk.

1

109

Cover image for Worked on an RLHF (Reinforcement

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.

0

83

Cover image for Trained a DreamBooth LoRA model

Trained a DreamBooth LoRA model to generate high-quality, personalized image outputs with consistent subject identity across different prompts and styles. The project involved dataset preparation, image captioning, and fine-tuning diffusion models using LoRA for efficient training and deployment. The solution enables fast generation of customized visuals while preserving subject consistency, style control, and high fidelity, suitable for creative, branding, and content generation use cases.

0

76

Muhammad Adrees

Lahore, Pakistan

AI Engineer | LLM Workflows & Agents for B2B SaaS

New to Contra

AI Engineer | LLM Workflows & Agents for B2B SaaS

Cover image for Email Intake Automation — Stips,

Email Intake Automation — Stips, Sorted Without a Human Touching Them The problem (any MCA ops person knows this pain)💯 Every funding application generates a flood of supporting documents ("stips") likd bank statements, tax returns, voided checks, business licenses, driver's licenses, landlord references, lease agreements, articles of incorporation, and dozens more. They arrive over days or weeks via email, attached as PDFs, JPGs, screenshots, and forwarded chains. They're named things like "scan_2.pdf" or "IMG_4847.jpeg". Someone on the ops team has to: download every attachment, figure out which application it belongs to, identify what kind of document it is, rename it properly, place it in the right folder in the case management system, and update the application checklist. For shops funding 50+ deals a week, this single workflow eats hours of operational labor every day. What I built🔥 - An intake pipeline that watches a shared inbox, pulls every attachment, identifies which application each one belongs to, classifies what type of stip it is, renames it to the firm's naming convention, drops it into the correct location, and updates the application's stip checklist automatically. - By the time a human looks at the case, it's organized. Outcomes🙌 - Stips routed and labeled without manual intervention - Application checklists update themselves - Funder/processor time freed up for actual review work - Reduced lost-document errors during back-and-forth with ISOs - Faster turnaround from "submission" to "ready for underwriting" Stack🧠 Python, IMAP/email processing, AI classification, async pipelines. Best fit for👍 MCA funders, ISOs, lenders, and any back-office operation that receives documents by email and burns hours sorting them. If your ops team manually downloads, renames, and routes attachments, this solves that.

0

39

Cover image for AI Bookkeeping Platform — Books

AI Bookkeeping Platform — Books That Maintain Themselves🔥 The problem💯 Small business owners don't want to think about bookkeeping. They want to know if the business is healthy, whether they can afford a new hire, and what their tax bill will look like. But getting answers from their books still requires effort, opening the app, navigating menus, running reports, interpreting numbers, and fixing categorization mistakes along the way. The tools have improved, but the workflow hasn't really changed, users still drive the software. What I built🙌 - A bookkeeping platform where the AI agent drives the workflow, not the user. - Instead of opening a dashboard and clicking through menus, users just ask. "How's revenue this month?" "Did I pay the AWS bill yet?" "Categorize the Amazon charge as Supplies and remember it." - The agent answers in plain language, takes real actions inside the books, creates rules from corrections, and only asks the user when something genuinely needs their input. The interface becomes the conversation. Outcomes🙌 - Users get answers without learning the app - Transactions get categorized and corrections become rules - Receipts auto-match to transactions - Reports update continuously, available on request - Bookkeeping shifts from a weekly chore to a quick chat Stack🧠 Python, GCP, event-driven architecture, LLM tooling, React, TypeScript. Best fit for👍 Fintech and SMB finance products, bookkeeping services going AI-native, accounting platforms exploring agent-first interfaces, or any product where the next product surface is a conversation, not a dashboard.

0

62

Cover image for Enterprise AI Personalization — Real-Time

Enterprise AI Personalization — Real-Time AI for Fortune 500 Retail The brands🔥 Built backend services and AI personalization infrastructure used by enterprise retailers including Samsung, Nissan, JCPenney, DICK'S Sporting Goods, and Fossil, products serving millions of shoppers in real time. The problem at scale💯 Enterprise ecommerce isn't like a small Shopify store. When millions of shoppers hit the site, every personalization decision needs to happen in milliseconds, every behavioral signal needs to be processed without losing data, and every campaign needs to run reliably across regions and devices. The hard part isn't the AI it's making sure the AI works under real production load, every day, for brands that can't afford downtime. What I built🔥 Event-driven backend services that turn high-volume shopper behavior (product views, cart activity, browsing patterns) into real-time signals for AI-driven personalization and campaign execution. Built on AWS Lambda for elastic scale, with API integrations supporting enterprise client launches and production-grade reliability. Outcomes🙌 - High-volume behavioral signals processed in real time - Event-driven Lambda pipelines supporting AI recommendation systems - Reliable infrastructure supporting enterprise brand campaigns - Production launches across multiple Fortune 500 retail brands Stack🧠 Node.js, AWS Lambda, event-driven architecture, REST APIs, ML-supporting infrastructure. Best fit for👍 Enterprise SaaS, ecommerce platforms, AI/ML companies, personalization products, CRO/growth tools, and anyone building backend systems where reliability at scale matters more than clever architecture.

0

50

Cover image for AI Agents & Workflow Automation

AI Agents & Workflow Automation — LLMs That Take Real Actions, Not Just Chat🔥 The problem💯 Most "AI agents" on the market are still chatbots wearing a costume. They can answer questions, summarize docs, and sound convincing but they can't actually do anything inside a real system. They don't update records. They don't call APIs. They don't make decisions that matter. When teams try to put them into production workflows, they either hallucinate, break under edge cases, or require so much guard railing that the agent becomes slower than the manual process it was supposed to replace. What I built🔥 - Production AI agents that operate inside real workflows, taking structured actions, calling internal tools and APIs, working through multi-step decisions, and knowing when to ask a human. - The agents handle the operational work teams actually want automated: querying data and answering follow-ups, classifying and routing incoming items, updating records, generating reports on request, running multi-step workflows that combine several tools, and recovering gracefully when something doesn't fit the expected pattern. Outcomes🙌 - Agents that take real actions, not just generate text - Tool using LLMs with structured outputs and validation layers - Multi-step workflows that complete reliably end-to-end - Audit logs so every agent action is reviewable - Human escalation built in agents know what they shouldn't decide - Evaluation suites so improvements can be measured, not guessed at Stack🧠 Python, LLM orchestration tooling, async pipelines, structured outputs, evaluation frameworks. Best fit for👍 SaaS products adding in-app AI assistants, ops teams automating internal workflows, fintech and back-office products with repetitive decision work, and any team that's tried building agents and watched them fall apart in production.

0

104

Lahore, Pakistan

I build offline AI tools that make documents talk.

New to Contra

I build offline AI tools that make documents talk.

Cover image for AuraExtract — Intelligent Invoice &

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

112

Cover image for AuraSort scans any folder and

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

124

Cover image for A fully offline document summarizer

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

122

Cover image for Built AuraChat v3.0 — a

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

127

Lahore, Pakistan

Web Developer building responsive and modern websites

Web Developer building responsive and modern websites

Cover image for I recently built an e-commerce platform for seamless online ...

I recently built an e-commerce platform for seamless online shopping and efficient product management, offering customers an intuitive experience to browse products, view details, compare prices, manage carts, and complete secure checkouts, while sellers can easily manage inventory, update listings, track orders, and monitor performance through a clean dashboard. The platform is designed with scalability and performance in mind, ensuring fast load times, responsive design, and reliable data handling across devices. Key Features: • Product browsing with detailed pages • Secure checkout and order management • Admin/seller dashboard for product and inventory control • Responsive, mobile-friendly UI • Modern and scalable architecture

0

97

Cover image for Built an MVP for a Metrominal Service AI Chatbot I recently ...

Built an MVP for a Metrominal Service AI Chatbot I recently developed an MVP for an AI-powered service chatbot designed for Metrominal. This generative chatbot helps users resolve issues instantly by understanding their queries, guiding them through solutions, and providing accurate responses in real time. The system is powered by a RAG (Retrieval-Augmented Generation) pipeline, enabling the chatbot to communicate directly with company data. It retrieves relevant documents, processes information, and generates context-aware answers, ensuring reliability and up-to-date results. The MVP demonstrates how AI can streamline customer support, reduce response times, and make organizational data easily accessible to end users through a natural, conversational interface.

0

89

Cover image for Introducing FarmFresh – Connecting Farmers and Consumers Dir...

Introducing FarmFresh – Connecting Farmers and Consumers Directly FarmFresh is a streamlined platform designed to bring farmers and consumers together with full transparency. Farmers can manage a dedicated dashboard where they add products, update prices, upload details, and share availability in real time. Consumers get a clear view of each product, including descriptions, pricing, farmer information, and live location on an interactive map. This creates a direct, trust-based buying experience and supports local agriculture. FarmFresh makes it easy for farmers to reach more customers and for consumers to access fresh, reliable, and locally sourced products.

0

95

Cover image for Introducing Quiz Hippo – Your

Introducing Quiz Hippo – Your AI-Powered Quiz Builder Quiz Hippo is a smart and flexible quiz app that lets you generate quizzes instantly from a prompt, text, URL, or PDF. Just upload your content, and the platform creates clear, accurate, AI-generated questions in seconds. You can build your own quizzes, solve quizzes created by others, track results, and easily share quizzes with friends, students, or teams. The interface is fast, simple, and built for anyone who wants a smarter way to learn or teach. Powered by modern AI and a robust tech stack, Quiz Hippo delivers high-quality question generation, seamless performance, and an engaging user experience. Tech Stack: Python, JavaScript, Node.js, React, LangChain, OpenAI

0

83

Lahore, Pakistan

AI Developer & ML Engineer: Top-notch Expertise

AI Developer & ML Engineer: Top-notch Expertise

Cover image for LLM Agents Cybersecurity workflow

LLM Agents Cybersecurity workflow

0

44

Cover image for Yolo v10 - Object Detection and tracking

Yolo v10 - Object Detection and tracking

0

321

Cover image for AI Agents workflow

AI Agents workflow

0

18

Cover image for Computer Vision - Detection and Segmentation with Yolo V9

Computer Vision - Detection and Segmentation with Yolo V9

0

51

Hammad Bin Sajjad

Lahore, Pakistan

Software Engineer with a commitment to excellence

Software Engineer with a commitment to excellence

Cover image for Pixel Character Sprites Generation

Pixel Character Sprites Generation

0

26

Cover image for Basic Social Media App

Basic Social Media App

0

8

Cover image for E-Commerce Website Clone

E-Commerce Website Clone

0

19

Cover image for Global Pixel Chat

Global Pixel Chat

0

11

Irtaza Ahmed Khan

Lahore, Pakistan

Machine Learning Engineer

Machine Learning Engineer

Cover image for Wasail: Demand Forecasting System

Wasail: Demand Forecasting System

0

6

Cover image for Natural Language Processing

Natural Language Processing

0

3

Cover image for Time Series Forecasting

Time Series Forecasting

0

4

Placeholder project card media

View more →