AI/ML Student & RAG Systems Builder_
Building from Python fundamentals toward super advanced Retrieval-Augmented Generation systems — the backbone of next-gen intelligent software.
Hey! I'm Pawandeep Singh, an AI/ML student living in Amsterdam, enrolled at the Amsterdam University of Applied Sciences.
My core obsession is Retrieval-Augmented Generation — the architecture that lets AI systems reason over vast knowledge bases in real time. I believe RAG is the backbone of the next wave of intelligent software.
I don't just want to use AI tools — I want to understand them deeply and build the infrastructure behind them, from embedding pipelines to production APIs.
Began the journey mastering Python — OOP, data structures, file I/O, and writing clean, production-ready code.
Enrolled at Amsterdam University of Applied Sciences. Studying ML algorithms, model training, and data pipelines.
Deep-diving into Retrieval-Augmented Generation — vector DBs, semantic search, and end-to-end LLM pipelines.
Goal: Deploy scalable, cloud-ready RAG systems and multi-agent AI architectures at enterprise scale.
A growing collection of notebooks exploring ML concepts — data pipelines, model training, and evaluation loops.
A question-answering system that ingests documents and answers queries using vector embeddings + LLM.
Production-grade RAG connecting PDFs, web, and databases with intelligent routing and re-ranking.
An agent system using RAG as its memory layer — capable of multi-step reasoning and task execution.
My goal is to build enterprise-grade RAG systems — intelligent search, document-aware AI assistants, and autonomous agents that operate at scale. The next generation of software will be knowledge-driven, and I'm building the skills to be at the forefront of that shift.
Always open to connecting with AI/ML enthusiasts, researchers, and builders. Whether you want to collaborate, share knowledge, or just talk RAG systems — reach out!