Available for opportunities

Muhammad Tayyab

AI Engineer · RAG · GenAI · Computer Vision · NLP

Dynamic AI engineer turning complex challenges into intelligent solutions. Specializing in RAG pipelines, LLM architectures, agentic AI systems, and production-grade ML applications.

RAG
GenAI
CV
NLP
🤖

Building Intelligent Systems

I'm a results-driven AI engineer with expertise in building end-to-end intelligent systems. From designing multi-agent RAG architectures to deploying real-time computer vision pipelines, I thrive on transforming complex problems into elegant, production-ready solutions.

Currently working at doAZ (Seoul, South Korea) as an AI Engineer, building enterprise-scale AI platforms for industrial safety management and real estate intelligence.

My research is focused on linguistic AI for low-resource languages — with a published paper on Hate Speech Detection for Roman Urdu.

1.5+
Years Exp
10+
Projects
1
Publication
AI / ML
GenAI RAG LLM Agentic AI Computer Vision NLP Fine-Tuning Speech Processing
Frameworks
FastAPI LangChain LangGraph LlamaIndex PyTorch TensorFlow Streamlit
Languages & Tools
Python C++ C Git / GitHub AWS S3
Databases & APIs
Qdrant FAISS Pinecone OpenAI Anthropic Deepgram Whisper

Work History

AI Engineer
doAZ · Seoul, South Korea (Remote)
APR 2025 – PRESENT

Leading end-to-end AI platform development for enterprise clients. Building multi-module intelligent systems integrating RAG pipelines, tool-calling agents, and FastAPI microservices. Designing bilingual (Korean/English) chatbots, real-time streaming architectures, and large-scale document processing systems for industrial and real estate sectors.

Python FastAPI RAG LangChain OpenAI Anthropic Qdrant AWS S3 LangGraph
AI Engineer Intern
doAZ · Seoul, South Korea (Remote)
OCT 2024 – APR 2025

Collaborated with the AI team to develop and enhance existing AI models. Researched new AI technologies including RAG architectures, vector databases, and LLM integrations. Contributed to the development of production-grade AI applications for Korean enterprise clients.

Python RAG Vector DBs LLMs Research

Featured Projects

🏭
Doosan Industrial Safety AI

Multi-module AI platform for industrial safety management. Integrates RAG, tool-calling agents, and FastAPI microservices powering Risk Assessment, Multi-Prompt AI, Ask Doosan AI, and Legal Compliance modules. Bilingual Korean/English chatbot with real-time streaming.

RAG AI Agent FastAPI Qdrant Anthropic
🏢
KT Estate AI System

Comprehensive modular AI system with 4 RAG pipelines and 4 agents for legal queries, document QA, multi-document summarization, construction drawing analysis, and Excel automation. Supports PDF, DOCX, XLSX, and image extraction with multi-language support.

RAG Multi-Agent AWS S3 OpenAI FastAPI
🎙️
AI Interviewer

Intelligent mock interview system based on the user's CV. Uses Gemini Flash 2.5 to generate interview questions, Deepgram TTS for speech output, and Deepgram STT to transcribe responses. Provides performance ratings out of 10 after the interview session.

TTS / STT Gemini Deepgram Python
🤝
HR AI Agent

Agentic AI system designed to automate and augment HR workflows. Handles candidate screening, question generation, and evaluation processes using advanced LLM reasoning and tool-use capabilities.

AI Agent LLM Python Agentic AI
🦺
PPE Safety Gear Detection

Real-time construction safety gear detection using YOLOv8. Monitors workers for helmets, goggles, gloves, vests, and boots via webcam. Trained on a custom-annotated dataset and deployed as a Streamlit web application with image/video upload support.

YOLOv8 Computer Vision Streamlit PyTorch
🛡️
CyberSentinel — Roman Urdu Hate Speech

Robust and linguistically-aware hate speech detection system for Roman Urdu. FYP and research project involving custom NLP pipeline, dataset curation, and model training. Tied to published research paper on Google Scholar.

NLP Deep Learning Research Python
🚲
Bike & Car Image Classification

Deep learning image classification model distinguishing between bikes and cars. Implements CNN-based architecture with data augmentation and transfer learning techniques for high-accuracy vehicle classification.

CNN Classification TensorFlow CV
🏠
Lahore House Price Prediction

Machine learning model predicting house prices for rent and sale in Lahore. Covers full data science pipeline including EDA, feature engineering, and regression modeling on real estate data from Pakistan's second-largest city.

ML Regression EDA Python
🔊
ZeroShot Voice Cloning System

Zero-shot TTS system that generates speech in the same voice as input audio. Uses MaskGCT for TTS conversion and Whisper for accurate transcription, enabling seamless voice cloning while maintaining naturalness and clarity.

TTS STT MaskGCT Whisper

Publications & Research

2025 · PUBLISHED
A Robust and Linguistically-Aware Hate Speech Detection System for Roman Urdu

A comprehensive NLP research contribution developing a robust hate speech detection system tailored to Roman Urdu — a low-resource, code-mixed language. The system leverages linguistically-aware modeling techniques to identify and classify hateful content in informal digital text, addressing a critical gap in multilingual AI safety research.

View on Google Scholar → GitHub Repository →

Academic Background

🎓
Bachelor of Science in Computer Science
The University of Lahore · Lahore, Pakistan
📅 2020 – 2024 ⭐ CGPA: 3.34 / 4.00 🔬 FYP: CyberSentinelRU

Let's Build Something Intelligent

I'm open to exciting AI engineering opportunities, research collaborations, and freelance projects. Whether you need a RAG system, a computer vision solution, or a full AI pipeline — let's talk.

Send a Message