Moiz AhmedMansoori
Building AI Systems That Work in the Real World.
// |
Specializing in Agentic Workflows, RAG pipelines, and scalable Machine Learning infrastructure. Building the bridge between foundational models and enterprise solutions.
About Me
BSAI Graduate from Dawood University of Engineering & Technology (Class of 2026). Specializing in Agentic AI, RAG pipelines, and production ML systems.
From building OCR-powered warranty detection systems at Atlas Battery to fine-tuning BERT transformers at CodeCelix to EEG signal processing at DUET — I've shipped AI in environments where it has to work reliably.
I design end-to-end: data pipelines, model training, SHAP explainability, and cloud deployment. Currently building multi-agent orchestration systems with LangGraph.
Currently Available
Experience
IT Intern (Software)
Atlas Battery Limited
- Developed AI-based Warranty Code Detection using EasyOCR and PaddleOCR integrated into the Claim Management System
- Built a LangChain-powered agentic chatbot connected to the company's internal knowledge base
- Built Power BI dashboards to visualize warranty claims and operational data, enabling the IT team to track claim resolution metrics in real time
Machine Learning Engineering Intern
CodeCelix
- Built ensemble models using AdaBoost and XGBoost on balanced and imbalanced datasets
- Handled class imbalance with class weighting and preprocessing techniques
- Fine-tuned BERT-based transformer models for NLP tasks with structured hyperparameter tuning
- Developed end-to-end ML pipelines from preprocessing to validation
Data Analysis Intern
Dawood University of Engineering & Technology
- Analyzed EEG signals for pattern recognition using statistical and ML approaches
- Developed real-time algorithms improving BCI output accuracy
- Assisted in research documentation and collaborated with faculty
Projects
QueryMind — NL2SQL Agent System
End-to-end LangGraph agent that translates natural language to SQL with auto-correction loops. Features pgvector semantic schema retrieval, a real-time observability dashboard for agent traces, and full-stack Next.js/FastAPI deployment handling 100k+ rows.
GIAIC Hackathon II - Spec-Driven Todo
A spec-driven task management system built across 5 phases — from a TDD CLI app to a cloud-native, AI-augmented full-stack platform with a LangChain chatbot, Docker/Kubernetes orchestration, and Vercel deployment with live analytics.
AIRO — AI Research Orchestrator
Multi-agent LangGraph system with 6 specialized AI agents for automated ML research: parallel model training, critic evaluation, SHAP explainability, and automated report generation. 18 experiments run, 12 models trained, best RandomForest f1_macro=0.7329.
Brain Tumor Detection
Achieved 94% classification accuracy on MRI brain tumor detection using a fine-tuned VGG-16 CNN trained on 7,200 images across 4 classes (glioma, meningioma, pituitary, no tumor). Pipeline includes OpenCV preprocessing, Grad-CAM visual explainability, and a full training-to-inference workflow.
Technical Capabilities
AI & Machine Learning
LLMs & Agentic AI
Data Science
Tools & Infrastructure
Education
Bachelor of Science in Artificial Intelligence
GraduatedDawood University of Engineering and Technology
Karachi, Pakistan
September 2022 - June 2026
Certifications
Certified Cloud Applied Generative AI Engineer (GenEng)
Governor House — GIAIC
Feb 2023 – Present
Get in Touch
I'm always open to discussing AI engineering opportunities, collaborations, or just geeking out about machine learning. Feel free to reach out!