Freelance AI Agent Engineers in LahoreFreelance AI Agent Engineers in Lahore
AI Integration & Automation Engineer | Full-Stack Web Apps
$50k+
Earned
65x
Hired
4.9
Rating
130
Followers
AI Integration & Automation Engineer | Full-Stack Web Apps
Claude, Codex AI SaaS | More Output, Less Tokens, Clean Code
7
Followers
Claude, Codex AI SaaS | More Output, Less Tokens, Clean Code
Scaling B2B revenue via advanced agentic automation.
New to Contra
Scaling B2B revenue via advanced agentic automation.
Cover image for Enterprise AI Outbound Engine: Programmatic
Enterprise AI Outbound Engine: Programmatic Domain Auditing & Hyper-Personalized Lead Acquisition The Objective To eliminate the extremely low conversion rates associated with generic, high-volume cold email strategies. This asset was engineered to build an automated, zero-latency outbound prospecting infrastructure that conducts programmatic technical audits on target company websites in real time. By delivering immediate, hyper-personalized value to a prospect’s inbox, the system dramatically increases cold response rates and shortens sales pipeline velocity. System Architecture & Workflow Breakdown The underlying logic is built as an asynchronous, multi-stage agentic data pipeline that seamlessly processes targets from raw data cells to a finalized outbound delivery: Stage 1: Automated Data Ingestion & Polling: The system monitors a centralized data core (Google Sheets) via automated webhooks, continuously scanning for newly appended prospect leads and tracking operational states to prevent duplicate processing. Stage 2: Programmatic Web Scraping: The workflow executes custom HTTP GET requests to isolate, scrape, and ingest live front-end code, metadata, and structural configurations directly from the target company's domain. Stage 3: Multi-Layered LLM Synthesis: The raw web payload is dynamically passed through dual-stage Large Language Model (LLM) API completion nodes. The first node isolates optimization bottlenecks on the prospect's site. The second node acts as a context-aware copywriter, translating those raw gaps into a polished, bespoke audit tailored specifically to the business owner. Stage 4: Automated SMTP Deployment: The finalized custom audit and strategic pitch are formatted into an email payload and routed through an automated mail-server node to deliver the value statement directly to the decision-maker. Stage 5: Closed-Loop State Sync: Upon successful delivery, a final write-back module updates the primary database row with full timestamp logs and execution states, establishing a clean audit trail. Core Capabilities & Tech Highlights Context-Driven Hyper-Personalization: Completely bypasses basic name-merge fields by extracting live, domain-specific text to generate authentic, high-impact value statements unique to every recipient. Token-Optimized Payload Ingestion: Employs advanced parsing to strip out irrelevant source code before sending data to the LLM core, preserving maximum contextual relevance while drastically lowering API computational costs. Scale-Ready Asynchronous Architecture: Engineered to execute complex web audits and custom draft writing sequentially across hundreds of target leads simultaneously without causing operational bottlenecks or memory overloads. Inbound Funnel Multiplier: Directly interfaces with modern outbound deliverability systems, protecting domain authority by replacing blind spam with highly targeted, consultative tech audits.
0
49
Cover image for Premium 3D Dental Infrastructure: Dynamic
Premium 3D Dental Infrastructure: Dynamic AI-Driven Conversion Engine The Objective: To modernize patient acquisition for high-end clinical practices by replacing outdated, static web layouts with an immersive, high-converting digital ecosystem. The Solution: Engineered a premium, fully responsive dental web infrastructure designed to capture high-value leads automatically. Moving completely away from traditional static pages, this platform utilizes high-performance dynamic components and fluid visual animations to build instant brand authority. The ecosystem features seamless lead generation architectures paired with a fully integrated, highly autonomous Agentic AI Chatbot to guide users from initial discovery to booking. Core Capabilities & Tech Highlights: Dynamic 3D Web Experience: Implements cutting-edge animations and interactive UI layers that break the mold of standard medical websites, significantly maximizing user session duration. Agentic AI Integration: Features an intelligent conversational agent—not a basic keyword-matching chatbot—capable of interpreting complex patient inquiries, qualifying leads, and handling advanced intent workflows autonomously. High-Conversion Lead Capture: Strategically positioned, interactive lead generation forms mapped to user behavior to maximize data capture while minimizing friction. Automated Intake Pipelines: Built to capture user interactions and route pre-qualified inquiry data directly to back-end administrative systems, removing operational drag. The Impact: Developed a scalable, high-retention blueprint for the healthcare sector that transforms passive web traffic into automated, pre-qualified customer pipelines.
0
45
ML AI | Backend | Computer Vision | GenAI | LLM Agents
New to Contra
ML AI | Backend | Computer Vision | GenAI | LLM Agents
Cover image for French Legal AI Assistant &
French Legal AI Assistant & Agentic RAG System Overview I designed, built, and deployed a specialized Legal AI Assistant for French lawyers using agentic RAG, legal data pipelines, vector search, reranking, open-source LLMs, and citation-grounded answer generation. The system allowed lawyers to ask legal questions and receive answers grounded in French law articles, legal references, and relevant judicial cases. Problem / Challenge Legal data is very different from normal document data. A generic RAG pipeline using fixed-size chunks often breaks legal meaning, misses important context, or retrieves incomplete references. The main challenges were: 🔹 Legal documents had different structures and lengths 🔹 Articles and laws could not be randomly split into fixed-size chunks 🔹 Each answer needed traceable legal references 🔹 Retrieval had to understand legal scope, not just semantic similarity 🔹 The system needed to reduce hallucinations for legal users 🔹 Deployment had to respect privacy and regulatory requirements My Expertise I worked as the Lead AI Engineer / Agentic RAG Developer responsible for the complete system design and implementation. My responsibilities included: 🔹 Legal data pipeline architecture 🔹 Document parsing and preprocessing 🔹 Custom legal chunking strategy 🔹 Vector database design 🔹 Agentic RAG workflow development 🔹 Retrieval optimization and reranking 🔹 Open-source LLM deployment 🔹 Backend API development with FastAPI 🔹 Secure Azure cloud deployment 🔹 Multi-tenant system support French Legal Data Engineering Pipeline I built an automated ETL pipeline to process thousands of French legal documents, articles, and judicial cases. The pipeline handled: 🔹 Raw legal document ingestion 🔹 Text cleaning and normalization 🔹 Legal article extraction 🔹 Section-aware document structuring 🔹 Custom chunk generation 🔹 Metadata extraction for article number, article title, section, source, and reference 🔹 Embedding generation 🔹 Vector database ingestion 🔹 Repeatable updates for future legal data expansion The chunking strategy was designed so legal articles were not cut in the middle or separated from their meaning. Agentic RAG Workflow Instead of using a simple one-step vector search, I built a LangGraph-based agentic RAG workflow. The workflow included: 🔹 User query understanding 🔹 Legal intent detection 🔹 Legal domain and scope identification 🔹 Generation of 2–5 targeted legal search queries 🔹 Retrieval of relevant chunks for each query 🔹 Deduplication of repeated results 🔹 Reranking of retrieved legal evidence 🔹 Source-grounded answer generation This improved tested retrieval accuracy from around 50% to 95%+. Retrieval, Citations & Case Law The retrieval system was designed to make answers transparent and verifiable. I implemented: 🔹 Vector search for semantic legal retrieval 🔹 Reranking to improve relevance 🔹 Metadata-based source traceability 🔹 Citation-backed answer generation 🔹 Article-level legal references 🔹 Typesense-based retrieval for French judicial cases 🔹 Supporting case law returned with legal answers This allowed lawyers to verify the exact legal source behind each generated response. Open-Source LLM & Cloud Deployment I evaluated and deployed open-source LLM infrastructure for private legal AI usage. The deployment included: 🔹 Qwen2.5:14B for French legal reasoning 🔹 Ollama and vLLM for model serving 🔹 Embedding and reranker models on a private Azure GPU VM 🔹 NVIDIA T4 16GB GPU optimization 🔹 Python/FastAPI backend APIs 🔹 Secure Azure deployment in the France region 🔹 Multi-tenant isolated access 🔹 GitHub CI/CD and Linux server management The system was designed for privacy, reliability, and regulatory compliance. Technologies Used 🔹 Python 🔹 FastAPI 🔹 LangChain 🔹 LangGraph 🔹 LangSmith 🔹 Ollama 🔹 vLLM 🔹 Qwen2.5:14B 🔹 ChromaDB 🔹 Typesense 🔹 Vector Databases 🔹 Reranking Models 🔹 Embedding Models 🔹 Azure Cloud 🔹 Linux 🔹 GitHub CI/CD Impact 🔹 Built a production-ready legal AI assistant for lawyers 🔹 Improved retrieval accuracy from ~50% to 95%+ in tested scenarios 🔹 Reduced hallucinations through citation-grounded generation 🔹 Enabled lawyers to verify answers using article and case references 🔹 Created a scalable legal data pipeline for thousands of documents 🔹 Deployed private open-source LLM infrastructure for legal compliance 🔹 Delivered a strong foundation for future legal AI workflows
0
80
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
93
Where Founder Vision Is Engineered into Agentic AI Products.
36
Followers
Where Founder Vision Is Engineered into Agentic AI Products.
Full Stack Web & Mobile Dev | Next Js | AI Agent | React
1x
Hired
5.0
Rating
28
Followers
Full Stack Web & Mobile Dev | Next Js | AI Agent | React
Sr.Full Stack Consultant and Developer with 8+ years of exp
$10k+
Earned
1x
Hired
5.0
Rating
13
Followers
Sr.Full Stack Consultant and Developer with 8+ years of exp
AI Automation Builder | Website Design
New to Contra
AI Automation Builder | Website Design