Skip to content
View Faraz6180's full-sized avatar
🎯
Focusing
🎯
Focusing

Block or report Faraz6180

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
Faraz6180/README.md

Faraz Mubeen Haider

Applied AI Engineer — Building LLM-powered document intelligence tools and shipping fast.

I'm a Software Engineering student at NUML(graduated) focused on applied AI systems. I specialize in rapid prototyping of LLM applications — particularly document processing, retrieval systems, and AI agents. I've shipped 11+ hackathon projects in 15 international competitions, including a win at the IBM Granite Hackathon.


What I Build

  • Document Intelligence — PDF parsing, semantic search, structured extraction
  • LLM Applications — RAG pipelines, AI agents, prompt engineering systems
  • Rapid Prototypes — Functional AI demos built in 48–72 hour sprints

Featured Work

AI Resume Analyzer for GCC Jobs

Live Demo: Hugging Face Space

An LLM-powered resume analysis tool that evaluates CVs for UAE, Saudi Arabia, and Qatar job markets. Extracts text from PDFs and generates ATS scores, job match ratings, and improvement suggestions using Groq's LLM API.

  • Tech: Python, Streamlit, Groq API, PyPDF
  • What I learned: PDF text extraction edge cases, prompt engineering for structured output, deploying to Hugging Face Spaces
  • Status: Functional prototype with live demo

InsightPilot AI

AI-powered document intelligence system that transforms unstructured PDFs into structured, queryable knowledge. Users can ask natural language questions over uploaded documents.

  • Tech: Python, LangChain, FAISS, Streamlit
  • Focus: RAG pipeline construction, vector embedding, semantic retrieval

AdvancedLeadsGeneration-AI — IBM Granite Hackathon Winner

LabLab.ai: Project Page

An intelligent lead generation system built during the IBM Granite Hackathon. Leverages IBM Watson and AI-driven discussion agents to assess and qualify potential clients.

  • Result: 🥇 Winner — IBM Granite Hackathon
  • Team: PolyEns
  • Focus: AI agent design, IBM Watson integration, business workflow automation

DevAI — DeepSeek Hackathon Finalist

LabLab.ai: Project Page

An AI-powered development workflow assistant that generates project-specific tutorials and provides context-aware code analysis.

  • Result: 🥈 Finalist — Fall in Love with DeepSeek Hackathon
  • Focus: LLM application design, developer tooling, context-aware prompting

Hackathon Track Record

Event Project Result
IBM Granite Hackathon AdvancedLeadsGeneration-AI 🥇 Winner
DeepSeek Hackathon DevAI 🥈 Finalist
Replit & Cursor Hackathon Byte Busters 🥈 Finalist
Agentic AI Hackathon (IBM watsonx) AI SOC Security Analyst Participant
Qubic Hack the Future AdmitWise Participant
AI for Connectivity Hackathon NetForAll Participant

Full profile: lablab.ai/u/@Faraz_Mubeen


Technical Focus

Languages: Python, SQL
AI/ML: LangChain, OpenAI API, Groq, FAISS, RAG systems, prompt engineering
Backend: FastAPI (learning), REST APIs
Deployment: Hugging Face Spaces, Streamlit Cloud
Data: PyPDF, pandas, document parsing

I do not list technologies I haven't used in projects.


Writing & Teaching

  • Stanford Code In Place — Section Leader (top 100 of 900+ applicants). Taught Python to international students.
  • Technical Writing — Publishing articles on Medium about RAG systems, LLM fine-tuning, and AI agents.

Currently Working On

  • Building production-ready RAG systems with evaluation frameworks
  • Learning FastAPI for robust AI backend development

Contact


> I build AI prototypes fast, learn from each one, and iterate toward production quality.

Pinned Loading

  1. ComplianceRAG ComplianceRAG Public

    Multi-agent RAG with a critic agent that scores groundedness and flags hallucinations in real time. FAISS + sentence-transformers + Gradio.

  2. data-quality-pipeline data-quality-pipeline Public

    Enterprise-grade anomaly detection and data governance system — deployable in one click on Hugging Face Spaces.

  3. AI-powered-Research-Assistant AI-powered-Research-Assistant Public

    AI-powered research assistant that retrieves and synthesizes information from ArXiv, Wikipedia, and the web using LangChain and Groq (Llama 3.3 70B), delivering fast, conversational insights throug…

    Jupyter Notebook 1

  4. VisualRAG VisualRAG Public

    VisualRAG is a multi-modal AI pipeline that lets you: Index images — YOLOv8 detects objects; CLIP encodes each image into a 512-d vector stored in FAISS Query with text — Ask any natural language q…

  5. HireMind-AI HireMind-AI Public

    AI Hiring Intelligence Platform that analyzes resumes against multiple jobs, detects skill gaps, optimizes resumes, generates cover letters, and provides ATS-based scoring using LLMs.

    Python 1

  6. sqlsense sqlsense Public

    Python