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.
- 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
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
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
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
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
| 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
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.
- 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.
- Building production-ready RAG systems with evaluation frameworks
- Learning FastAPI for robust AI backend development
- 📧 Email: faraz.outreach8@gmail.com
- 💼 LinkedIn: linkedin.com/in/farazmubeen-ai
- 🏆 LabLab.ai: lablab.ai/u/@Faraz_Mubeen
- 📝 Medium: [Your Medium URL]
> I build AI prototypes fast, learn from each one, and iterate toward production quality.