~/blog
Articles, tutorials, and posts.
Fine-tuning a language model on domain knowledge sounds manageable until you estimate the labor involved. A single high-quality instruction-response pair might…
A Python-first walkthrough of the data structures and techniques that show up in coding interviews and real systems work.
A comprehensive guide to machine learning — from fundamentals to advanced techniques
SQL Agent with MLflow Observability Architecture SQL Agent with MLflow Observability User Natural language SQL question SQL Agent LangChain + NVIDIA ReAct / Too…
A practical, end‑to‑end guide to building a synthetic data pipeline for LLM fine‑tuning, covering single‑turn and multi‑turn conversation generation, chain‑of‑thought reasoning, and intelligent data creation from raw text using Self‑Instruct, agentic workflows, and NVIDIA NeMo Data Designer.
The Problem We're Solving Evaluating RAG (Retrieval-Augmented Generation) systems is challenging. You need: - Ground truth Q&A pairs that accurately reflect you…
A human-friendly guide to curating, cleaning, and composing datasets that give large language models their skills and personality—covering data quality, deduplication, annotation, synthesis, and governance, framed as a modern alchemist’s craft.
A beginner-friendly, pen-and-paper walkthrough of contrastive learning for text embeddings, from simple averaging encoders and InfoNCE loss to state-of-the-art models like SimCSE and Qwen3 Embedding, revealing how vectors capture meaning and power modern semantic search.
Welcome to this comprehensive guide on building a multimodal Retrieval-Augmented Generation (RAG) system! In this tutorial, we'll create an AI assistant that ca…
A practical framework for testing agentic AI beyond unit tests—covering tools, planning, memory, and resilience. Real-world failures, research-backed metrics, and a maturity model to ensure your agent earns user trust.
Learn the fundamentals of recursion and how to think recursively in Python
AI is handling the execution. Your edge is knowing how to design what it builds, evaluate what it produces, and validate it in the real world.
Building AI agents isn't just about picking a model. It's about making deliberate decisions under constraint — and understanding what you're giving up every time.
A comprehensive guide to learning statistics and probability
A comprehensive guide to learning Python programming from scratch
Hands-on Quantization by hand and numpy with detailed explanation.
Hands-on how human-in-the-loop work behind the scene in long and complex workflows.
A practical deep dive into designing microservices for AI and ML systems, focusing on real-world challenges like latency, scaling, fault tolerance, and system reliability. Written from a distributed systems perspective, not MLOps or model training.