Parikshit Sharma

@parikshitiiib

Building RAG systems and MLOps pipelines in production. Writing the docs I wish existed.

Bangalore, IndiaJoined April 2026

About

Senior AI/ML Engineering Leader building production AI systems that scale. I work at the intersection of LLMs, MLOps, and distributed systems turning experimental prototypes into enterprise-grade platforms.

Available for

Nothing here yet.

Parikshit Sharma's blogs

Parikshit | AI Systemsparikshitiiitb.hashnode.dev2 posts

Articles Threads Comments

Recently published

PSParikshit Sharmaparikshitiiitb.hashnode.dev

0

RAG Chunking Strategies: What Actually Works in Production (And What Quietly Destroys Retrieval Quality)

Apr 22 · 6 min read · Every RAG tutorial shows you fixed-size chunking in five lines of code. Nobody shows you what happens six months later when your retrieval quality has collapsed and you can't figure out why. This arti

Join discussion

PSParikshit Sharmaparikshitiiitb.hashnode.dev

2

Production RAG System Design: Retrieval Quality, Hallucination, and Latency in LLMs

Apr 20 · 4 min read · Retrieval-Augmented Generation (RAG) systems are widely used to improve the accuracy of Large Language Models (LLMs) by grounding responses in external data. While most tutorials demonstrate simple im

AArchit and 1 more commented

Parikshit Sharma

About

Available for

Parikshit Sharma's blogs

Recently published

RAG Chunking Strategies: What Actually Works in Production (And What Quietly Destroys Retrieval Quality)

Production RAG System Design: Retrieval Quality, Hallucination, and Latency in LLMs

Search Hashnode

Parikshit Sharma

About

Available for

Parikshit Sharma's blogs

Recently published

RAG Chunking Strategies: What Actually Works in Production (And What Quietly Destroys Retrieval Quality)

Production RAG System Design: Retrieval Quality, Hallucination, and Latency in LLMs