Skip to content
View santoshshinde2012's full-sized avatar
🏠
Working from home
🏠
Working from home
187 followers · 318 following

Achievements

Achievement: Pair Extraordinairex2Achievement: Starstruckx2Achievement: Pull Sharkx3Achievement: YOLOAchievement: Quickdraw

Achievements

Achievement: Pair Extraordinairex2Achievement: Starstruckx2Achievement: Pull Sharkx3Achievement: YOLOAchievement: Quickdraw

Highlights

Block or report santoshshinde2012

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
santoshshinde2012/README.md

Hi 👋, I'm Santosh Shinde

AI Engineer Lead · Systems thinker · Writer

I'm an AI Engineer Lead at Syngenta, based in Pune. I design and ship LLM-powered products — RAG pipelines, evaluation loops, and the MLOps plumbing that keeps them running in production. I came up as a full-stack engineer (TypeScript, Node, React, AWS) and grew into ML and generative AI from there. Working across the full surface taught me one thing most posts skip: a model is the easy part. The hard part is everything around it — retrieval, evals, failure modes, cost, the team that has to maintain it six months from now. That's what I find interesting, and it's what I write about. What I focus on

End-to-end systems — not the model in isolation, the full pipeline. Most of the value (and most of the bugs) lives between the boxes on the architecture diagram. Tradeoffs that matter to the business — Lakebase vs Lakehouse, batch vs streaming, RAG vs fine-tuning. These show up in latency, cost, and risk, not just engineering preference. The unglamorous production work — eval harnesses, observability for non-deterministic systems, drift, guardrails. The stuff that separates a demo from something you can trust on a Tuesday morning.

Blog Posts

Pinned Loading

  1. node-boilerplate node-boilerplate Public template

    Node Typescript Boilerplate for Microservices. Skeleton for Node.js Apps written in TypeScript (with Setup Instructions for ESLint, Prettier, and Husky)

    TypeScript 464 84

  2. ng-keycloak ng-keycloak Public

    ng-keycloak

    TypeScript 6 3

  3. micro-frontends-mindmaps micro-frontends-mindmaps Public

    A mindmap summarising micro-frontends concepts

    40 6

  4. nestjs-mindmaps nestjs-mindmaps Public

    A mindmap summarising nestjs concepts

    29 2

  5. node-ts-sequelize-pg-boilerplate node-ts-sequelize-pg-boilerplate Public template

    NodeSeQ - Node Typescript Sequelize PostgreSQL Boilerplate

    TypeScript 5 2

  6. multi-factor-authentication multi-factor-authentication Public

    2FA TOTP implementation using Node.js, TypeScript, and React.js

    TypeScript 6 3