Muhammad Ahmad Faizan
AI & Backend Engineer | AI Systems & Automation
New to Contra
Muhammad Ahmad is building their profile!
Shopify Email Marketing Automation with Zapier & Klaviyo
Designed and implemented automated email marketing workflows for a Shopify store using Zapier and Klaviyo. Created automation flows for welcome emails, abandoned cart recovery, personalized product recommendations, customer segmentation, and follow-up campaigns. Helped streamline marketing processes by connecting business tools and automating customer engagement throughout the purchasing journey.
0
17
AI-Powered Sales Outreach & Lead Generation Automation SystemAI-Powered Sales Outreach & Lead Generation Automation System.
Built a complete AI-powered B2B lead generation and outreach automation system using n8n, SerpAPI, and Groq LLM. The system automatically discovers businesses worldwide by niche and location, analyzes each company using AI to identify pain points, generates personalized cold emails with HTML templates, saves all leads to a Google Sheets CRM, and runs automated follow-up sequences. The system contacts 100+ businesses daily with zero manual work, featuring duplicate detection, blacklist management, and real-time reporting.
0
20
AI Resume Screening SaaS Platform with FastAPI & NLP
Developed an AI-powered SaaS platform to streamline the recruitment process by automating resume screening and candidate management. Built a scalable FastAPI backend with PostgreSQL, secure JWT authentication, and REST APIs. Implemented NLP-based skill extraction using spaCy to match candidate resumes with job requirements, enabling efficient filtering, search, and analytics for recruiters.
1
37
AI Customer Support Agent with Tool-Calling & Mock CRM
Built a FastAPI-based customer support agent that uses LLM tool-calling to look up orders, retrieve customer info, and escalate or process refunds against a mock CRM (SQLite). Implemented a full agent loop: the model decides when a tool is needed, Python executes it, and the result feeds back into the conversation. Added session-based memory with automatic summarization for long conversations, plus guardrails to keep the agent on-topic. Designed as the foundation for tool-calling patterns reused in later multi-agent work.
0
28
Built a Retrieval-Augmented Generation backend using LangChain and Qdrant: PDF upload and chunking, embedding generation, semantic search, and answer synthesis with inline page-level citations. Diagnosed and fixed a silent fallback bug where missing LLM credentials caused raw chunk dumps instead of real generated answers, then migrated the chat backend to Groq (LLaMA 3.3 70B) for fast, free-tier inference. Supports multi-document querying and follow-up question rewriting for conversational retrieval.
0
31
Designed a multi-agent research system using LangGraph, orchestrating planner, researcher, analyzer, and writer agents with shared state and conditional looping. Includes a human-in-the-loop step where users approve or edit the research plan before execution, live progress streaming via SSE, and a full decision trace for transparency. Debugged production-style issues including an event-loop freeze from an unbounded blocking API call and a token-limit failure from oversized prompts. Built a React frontend with a custom black-theme UI and logo.
0
42