I enjoy building backend systems and understanding how different parts of an application work together.

My background in Mathematics shaped the way I approach engineering:

understand the problem → break it down → build carefully → measure → improve

I started with backend APIs, databases, authentication, testing, caching, and deployment.

Now I am applying that foundation to AI systems, especially Retrieval-Augmented Generation (RAG), where I am building the pipeline from scratch and improving it one version at a time.

A document question-answering system built from first principles to understand how retrieval systems actually work.

Instead of starting with orchestration frameworks, I built the pipeline step by step and gradually improved:

• how documents are processed
• how relevant information is found
• how results are ranked
• how larger context is recovered
• how unnecessary context is removed
• how final answers stay grounded in the source

The project has now progressed through multiple versions, with each version adding one major idea.

Current progression:

Basic RAG
   ↓
Hybrid Retrieval
   ↓
Reranking
   ↓
Metadata Filtering
   ↓
Parent-Child Retrieval
   ↓
Context Compression

🔗 Repository https://github.com/imLeo007/rag-from-scratch-v7

A backend API built to understand how caching can make repeated reads faster while keeping data correct.

The main lesson from this project was simple:

Performance is useful only when correctness is preserved.

It helped me understand cache hits, cache misses, expiration, invalidation, database consistency, and multi-service backend applications.

Repository https://github.com/imLeo007/user-profile-cache-api

Live API https://user-profile-cache-api.onrender.com/docs

A small AI tutoring application where users can sign in, ask questions, and keep their previous conversations.

This project helped me understand how an AI model fits inside a normal application.

The model generates the answer, while the backend handles:

• users
• authentication
• conversation history
• persistence
• application flow

This became the bridge between my backend development work and the RAG systems I started building afterward.

Repository https://github.com/imLeo007/ai-tutor-lite-v1

I prefer learning systems from the inside out.

Understand the purpose
        ↓
Design the architecture
        ↓
Reason through the algorithm
        ↓
Build it
        ↓
Debug each layer
        ↓
Measure what happens
        ↓
Improve the real problem

This is why I am building RAG systems from scratch before depending heavily on higher-level frameworks.

My current focus is on improving retrieval and context quality in AI applications.

I am working toward:

Better Retrieval
      ↓
Context Quality
      ↓
RAG Evaluation
      ↓
Memory
      ↓
Tool Calling
      ↓
Reliable AI Workflows

The goal is not simply to connect models to APIs.

I want to understand how to build AI systems that are useful, grounded, measurable, and reliable.

I am growing toward Backend / AI Engineering, with a long-term interest in building intelligent products that solve real problems.

My main focus is becoming stronger at:

• backend system design
• retrieval systems
• debugging and performance
• AI application architecture
• building reliable products from first principles