Freelance Data Engineers in PunjabFreelance Data Engineers in Punjab
ProjectsPeople
Mirza Umer's avatar
Mirza Umer
Sialkot, Pakistan
AI Chatbot and Automation Expert
New to Contra
AI Chatbot and Automation Expert
Cover image for The client was losing high-value
The client was losing high-value business leads due to delayed follow-ups and manual data entry across disconnected platforms (CRM, email, and advertising channels). The internal team was spending upwards of three hours a day manually copying lead data, resulting in data fragmentation and an average response time of over 12 hours. The Tech Stack 1. n8n (Advanced Workflow Orchestration). 2. Webhooks & REST APIs (Data Ingestion). 3. PostgreSQL / Airtable (Centralized Data Warehouse). 4. Slack API (Instant Internal Notifications). The Solution. I engineered an autonomous, multi-stage lead processing engine using n8n. The system captures inbound leads via instant webhooks from front-end marketing platforms, normalizes and enriches the data using secondary API lookups, and instantly populates the centralized data warehouse. Simultaneously, the workflow routes the lead based on custom logic (such as budget or region) and fires an immediate, structured notification to the sales team's Slack channel, allowing for a sub-5-minute response time. The Business Impact. The automated pipeline eliminated manual data entry, recovering roughly 15 hours of administrative time per week for the internal team. More importantly, reducing the lead response time from 12 hours down to under 5 minutes directly improved lead-to-opportunity conversion rates by over 30%.
0
33
Cover image for The legal services firm required
The legal services firm required a highly secure, instantaneous method for employees to query a massive internal knowledge base of over 200 complex contracts and compliance documents. The existing manual search process was highly inefficient, taking employees an average of 15 minutes per query and creating significant operational bottlenecks. The Tech Stack 1. Python (Data Ingestion & Formatting). 2. LangChain (RAG Orchestration). 3. Pinecone (Vector Database). 4. OpenAI GPT-4 (Contextual Synthesis). 5. Streamlit (Custom Web Interface). The Solution I engineered a secure Retrieval-Augmented Generation (RAG) pipeline to automate document retrieval. The system ingests and chunks hundreds of legal documents, storing them in a Pinecone vector database. When an employee submits a query, the system retrieves the most relevant semantic chunks and uses GPT-4 to synthesize a coherent response. To ensure zero hallucinations regarding strict legal terminology, the retrieval pipeline is engineered to explicitly cite its sources (e.g., "According to NDA_Template.pdf, Page 4") for every generated answer. The Business Impact The chatbot successfully reduced the time employees spent searching for specific legal clauses from an average of 15 minutes per query down to mere seconds. This drastically improved team productivity, reduced billable hour bloat, and ensured absolute accuracy in document retrieval.
0
58
Cover image for Umair Pets Clinic in Sialkot
Umair Pets Clinic in Sialkot had thousands of Facebook followers and strong reviews but no website or online booking system. I built them a complete booking platform on Base44 including a client booking flow, a staff dashboard, and an automated confirmation system that emails the pet owner and updates the dashboard the moment a booking is made. The live site is at umairpetsclinic.base44.app (http://umairpetsclinic.base44.app). Built for the Base44 Give It A Glow Challenge. #base44giveitaglowchallenge #GiveItAGlow @base44 https://x.com/MirzaUmerContra/status/2076317805700698525
1
122
Cover image for Premier Dental's front desk was
Premier Dental's front desk was overwhelmed with repetitive appointment inquiries during peak hours. This volume caused excessive hold times, missed calls, and ultimately, lost booking opportunities. The staff needed a way to offload routine scheduling without sacrificing the natural, empathetic tone expected in healthcare. The Tech Stack 1. Vapi (Low-Latency Voice AI Infrastructure). 2. Custom LLM System Prompts (Conversational Logic). 3. REST API (Real-Time Calendar Synchronization). 4. Twilio (Telephony Integration). The Solution: I deployed an autonomous, low-latency AI voice agent named "Sarah" to handle inbound calls 24/7. Engineered on the Vapi platform, the agent answers calls instantly, greets patients naturally, and collects necessary intake details (name, preferred date, appointment type). Through REST API integrations, the system checks availability, confirms new bookings, and reschedules existing appointments in real time, while intelligently escalating complex edge cases to a human receptionist. The Business Impact: The voice agent successfully handled 1,240 inbound calls with an 87% resolution success rate and an average call duration of 2 minutes and 34 seconds. By eliminating front desk call overflow, the clinic ensured zero missed booking opportunities, allowing the human staff to focus exclusively on high-touch, in-person patient care.
0
31
Data Engineer(2)
Arslan Mehmood's avatar
Arslan Mehmood
Lahore, Pakistan
ML AI | Backend | Computer Vision | GenAI | LLM Agents
New to Contra
ML AI | Backend | Computer Vision | GenAI | LLM Agents
Cover image for AI-Powered PDF Data Extraction My role:
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
61
Cover image for LakeShield - AI-Powered Video Monitoring
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
80
Cover image for Shelfr - AI-Powered Retail Shelf
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
62
Cover image for ⚖️ Built a French Legal
⚖️ 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
62
Data Engineer(1)
Umaima Iqbal's avatar
Umaima Iqbal
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
141
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
144
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
139
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
145
Data Engineer(1)
Arham Malik's avatar
Arham Malik
Rawalpindi, Pakistan
Backend & AI engineer who ships systems fast and scale.
New to Contra
Backend & AI engineer who ships systems fast and scale.
Cover image for Imagine having over 100 different
Imagine having over 100 different data sources all over the place. That was the problem Apex Analytics solved. I built this big data platform on Google Cloud using BigQuery and ETL pipelines that clean, transform, and unify everything. The frontend is React based, so stakeholders can see real time KPIs without waiting forever. Queries come back in under a second even with millions of records. It felt like solving a giant puzzle, but the result was a super reliable analytics hub that the entire company trusted. For more details, please visit: https://arham-nexus.vercel.app/work/apexanalytics
0
66
Cover image for This is a classic enterprise
This is a classic enterprise academic portal, but built solid. It uses  Web Forms, ASP.NET, C#, and SQL Server. The main challenge was role based access control because you have admins, faculty, TAs, and lab demonstrators all needing different permissions. I designed a three tier architecture with stored procedures and optimistic concurrency control so data doesn’t get messed up when people edit at the same time. Over 200 users per semester use it for task assignments and progress tracking. It’s not flashy, but it works perfectly. For more details, please visit: https://arham-nexus.vercel.app/work/talabportal
0
39
Cover image for Skill Swap is a peer
Skill Swap is a peer to peer learning platform where you can be both a student and a teacher. I built the backend with Java Spring Boot, real time chat with WebSockets, and video calls with WebRTC. The matching algorithm finds people based on skills, ratings, and availability. You can switch roles anytime. It also has a trust based review system so fake reviews don’t ruin it. This was an MVP, but it proved that real time learning communities can work really well. For more details, please visit: https://arham-nexus.vercel.app/work/skillswap
0
59
Cover image for This is a native Android
This is a native Android app I built with Kotlin and Firebase. It connects tourists with verified local guides in real time. You open the app, see nearby guides, book a tour, and then you can track each other’s location live using Google Maps. I also added offline support because travel doesn’t always have perfect internet. Over 100 active users ended up using it,during the MVP. The best part? Battery usage was optimized so your phone doesn’t die halfway through the day. Really proud of how smooth it turned out. For more details, please visit: https://arham-nexus.vercel.app/work/raaheraast
0
60
Data Engineer(1)
Attaul Mohiman's avatar
Attaul Mohiman
Multan, Pakistan
"Full Stack Developer with extensive experience "
"Full Stack Developer with extensive experience "
Cover image for Challenge is a live fitness
Challenge is a live fitness platform that transforms health goals into team-based competitions. It combines gamified daily tasks with robust social networking to drive consistent user engagement. Competitive Logic: Organizers can configure 2 or 4 teams and set custom challenge durations. Point System: Users complete daily tasks and questionnaires. Scores are logged and reset to 0 every 24 hours. At the end of the week, the system calculates totals to crown a winning team. Social Ecosystem: Includes private groups, personal chats, and social feeds. Users can publish articles, create custom challenges, and join global fitness events.
1
101
Cover image for I’m building an automated pipeline
I’m building an automated pipeline for a celebrity news YouTube channel: trending stories are sourced, scripts generated with AI, media collected, voiceovers added, and videos edited—all with Slack review and ready-to-upload drafts. 💡 This project shows how AI and automation can keep content fresh while cutting manual work. 🚀 Curious to see it in action or build your own? Let’s connect!
4
1
145
Cover image for Taxiee – Smart, Safe &
Taxiee – Smart, Safe & Reliable Ride Booking Taxiee is a modern ride-booking app designed to make everyday travel simple, fast, and dependable. Whether you’re commuting to work, heading to the airport, or booking a ride for someone else, Taxieea connects you with trusted drivers in just a few taps. Key Features Easy ride booking with live driver tracking Multiple ride options to fit your needs and budget Secure payments and clear fare estimates Real-time notifications and trip updates Taxiee is built with reliability and user comfort at its core—combining clean design, fast performance, and smart technology to move you where you need to go, stress-free. Book smarter. Ride safer. Travel better with Taxieea.
1
1
106
Cover image for Greening is an environmental monitoring
Greening is an environmental monitoring app designed to help users track and analyze the impact of green spaces. The app allows users to post and manage sites, monitor the amount of CO₂ absorbed and O₂ produced by trees, and evaluate environmental health over time. Data is visualized through interactive graphs and touch-enabled charts, enabling clear insights and informed decision-making. Greening empowers individuals and organizations to understand, protect, and manage nature using advanced, data-driven tools.
1
4
141
Data Engineer(1)