Writing

Articles &
Insights

Technical depth on AI/ML engineering-from LLM fine-tuning and RAG architecture to production systems and applied research.

2026

Apr 28

LLM Fine-Tuning: LoRA and QLoRA Explained Simply

This article explains how LoRA and QLoRA work, why they are efficient, and when to use them in practical model adaptation workflows.

#Machine Learning#LLM#LoRA#QLoRA

Apr 16

ML Model Deployment Strategies on Google Cloud

A practical guide to choosing between Vertex AI Endpoints, Batch Prediction, Cloud Run, GKE, Kubeflow, and edge patterns for machine learning inference on Google Cloud.

#google-cloud#vertex-ai#mlops#deployment

Apr 16

ML Model Deployment Strategies on AWS

A practical guide to choosing between SageMaker endpoints, EKS, ECS, Lambda, Kubeflow, and edge deployment patterns for machine learning inference.

#aws#sagemaker#mlops#deployment

Apr 15

Optimizing RAG Pipelines

A practical guide to improving RAG pipelines through better retrieval, chunking, reranking, evaluation, and operational design.

#rag#llms#retrieval#evaluation

2025

Dec 30

Activation Functions

Activation functions are the decision-makers of neural networks — they introduce non-linearity, enable feature selection, and determine whether learning can happen at all. A practical guide to Sigmoid, Tanh, ReLU, Leaky ReLU, and Softmax.

#machine-learning#deep-learning#neural-networks

Dec 29

Hyperparameter Tuning in AWS SageMaker

Machine learning models have two kinds of parameters: weights learned from data, and hyperparameters set before training. Finding the right combination of the latter is what separates converging models from failing ones.

#machine-learning#aws#sagemaker#mlops