https://nikhil-chigali.github.io/I'm Nikhil, an AI & ML engineer working on Agentic AI, RAG systems, and LLMOps. I build LLM pipelines that run in production: hybrid retrieval, multi-agent coordination, evaluation frameworks, and the monitoring to keep them reliable. Previously an ML & DS Consultant at Microsoft; MS CS from Rice University. 2026-04-19T17:15:27+00:00 Nikhil Chigali https://nikhil-chigali.github.io/ Jekyll © 2026 Nikhil Chigali /assets/img/favicons/favicon.ico /assets/img/favicons/favicon-96x96.png 2018-07-06T18:30:00+00:00 2018-07-06T18:30:00+00:00 https://nikhil-chigali.github.io/posts/simple-perceptron-training-algorithm/ Nikhil Chigali

This post was originally published on Medium on July 7, 2018. View original article. There’s this quote I love from Bill Gates: “I choose a lazy person to do a hard job. Because a lazy person will find an easy way to do it.” That’s honestly how I think about AI. We’re trying to solve some really hard problems, so we look around for the easiest path, and more often than not, nature has already...

2018-06-28T18:30:00+00:00 2018-06-28T18:30:00+00:00 https://nikhil-chigali.github.io/posts/logistic-regression-in-a-nutshell/ Nikhil Chigali

This post was originally published on Medium on June 29, 2018. View original article. Get ready to classify some data! Logistic regression is a supervised ML algorithm. A bit of calculus, probability, and statistics will go a long way here. Problem Setup Say we have a training dataset with binary labels (0 or 1). We want to train a model that tells us the probability of a sample belonging ...

2018-06-20T18:30:00+00:00 2018-06-20T18:30:00+00:00 https://nikhil-chigali.github.io/posts/maximum-likelihood-estimation/ Nikhil Chigali

This post was originally published on Medium on June 21, 2018. View original article. Probability Basics Probability is the chance of an event $A$ occurring out of all possible events in the sample space $S$: [P(A) = \frac{ A }{ S }] Joint Probability Joint probability is when multiple events occur at the same time. For events $A$ and $B$:...

2018-06-17T18:30:00+00:00 2018-06-17T18:30:00+00:00 https://nikhil-chigali.github.io/posts/gradient-descent-backbone-of-ml-algorithms/ Nikhil Chigali

This post was originally published on Medium on June 18, 2018. View original article. Introduction to Machine Learning Before I get into gradient descent, let me quickly walk through how I think about machine learning. Almost every ML algorithm boils down to four steps: Define a model Make predictions on the training data Calculate the prediction error Tune the model’s weights to r...