Perivitta Rajendran

Jun 8, 2026

Context Engineering: The New Skill That Is Replacing Prompt Engineering

Prompt engineering is giving way to something deeper: context engineering. How you structure what goes into the context window, what you include,...

blogpost· 26 mins read ·Intermediate

Jun 7, 2026

ai-engineering

Vision Language Models (VLMs): How GPT-4o, Claude, and LLaVA Understand Images

Vision Language Models bridge the gap between pixels and language. This post covers how CLIP encodes images, how visual tokens are projected...

ai-engineering· 45 mins read ·Advanced

Jun 6, 2026

ai-engineering

Mixture of Experts (MoE): The Architecture Behind GPT-4, Mixtral, and Grok

Mixture of Experts scales model capacity without scaling compute. Instead of activating all parameters for every token, MoE routes each token to...

ai-engineering· 47 mins read ·Advanced

Jun 5, 2026

blogpost

Diffusion Models Explained: The Math-Free Guide to How Stable Diffusion and DALL-E Work

Diffusion models generate images by learning to reverse a noise process. No math required. Here is the intuition behind Stable Diffusion, DALL-E,...

blogpost· 34 mins read ·Beginner

Jun 4, 2026

blogpost

AI Agent Memory: Short-Term Context, Long-Term Storage, and Episodic Recall

Stateless LLMs forget everything when the context window closes. Building agents that actually remember requires understanding four distinct memory types and when...

blogpost· 29 mins read ·Intermediate

Jun 3, 2026

blogpost

Reasoning Models Explained: How o1, o3, and DeepSeek R1 Think Before They Answer

Reasoning models like o1, o3, and DeepSeek R1 don't just predict the next token. They think through problems step by step before...

blogpost· 27 mins read ·Intermediate

Jun 2, 2026

ai-engineering

LoRA and QLoRA: Fine-Tuning LLMs on a Single GPU

Full fine-tuning a 7B parameter model requires 112 GB of VRAM and costs thousands of dollars. LoRA reduces trainable parameters by 99%...

ai-engineering· 24 mins read ·Advanced

Jun 1, 2026

ai-engineering

Graph RAG: When Knowledge Graphs Beat Vector Search

Standard vector RAG fails on multi-hop questions that require connecting information across multiple documents. Graph RAG solves this by building a knowledge...

ai-engineering· 24 mins read ·Advanced

May 31, 2026

ai-engineering

LLM Evaluation Pipelines: How to Test What Your Model Actually Does

Standard unit tests cannot evaluate LLM outputs because the same question can have dozens of correct answers. This post covers LLM-as-judge scoring,...

ai-engineering· 27 mins read ·Intermediate

May 30, 2026

ai-engineering

Semantic Caching for LLMs: Cut Your API Bill by 60%

Exact-match caching fails for LLMs because users never ask the same question twice in identical words. Semantic caching solves this by comparing...

ai-engineering· 39 mins read ·Intermediate

Perivitta Rajendran

Recent writing

LLM as Judge: How to Evaluate AI Models Automatically at Scale

Edge AI: Running LLMs on Your Phone Without the Cloud

AI Coding Assistants in 2026: Cursor, GitHub Copilot, and the Future of Software Development

From the archive

Context Engineering: The New Skill That Is Replacing Prompt Engineering

Vision Language Models (VLMs): How GPT-4o, Claude, and LLaVA Understand Images

Mixture of Experts (MoE): The Architecture Behind GPT-4, Mixtral, and Grok

Diffusion Models Explained: The Math-Free Guide to How Stable Diffusion and DALL-E Work

AI Agent Memory: Short-Term Context, Long-Term Storage, and Episodic Recall

Reasoning Models Explained: How o1, o3, and DeepSeek R1 Think Before They Answer

LoRA and QLoRA: Fine-Tuning LLMs on a Single GPU

Graph RAG: When Knowledge Graphs Beat Vector Search

LLM Evaluation Pipelines: How to Test What Your Model Actually Does

Semantic Caching for LLMs: Cut Your API Bill by 60%

Recent writing

LLM as Judge: How to Evaluate AI Models Automatically at Scale

Edge AI: Running LLMs on Your Phone Without the Cloud

AI Coding Assistants in 2026: Cursor, GitHub Copilot, and the Future of Software Development

Not sure where to start? Just ask.

From the archive

Context Engineering: The New Skill That Is Replacing Prompt Engineering

Vision Language Models (VLMs): How GPT-4o, Claude, and LLaVA Understand Images

Mixture of Experts (MoE): The Architecture Behind GPT-4, Mixtral, and Grok

Diffusion Models Explained: The Math-Free Guide to How Stable Diffusion and DALL-E Work

AI Agent Memory: Short-Term Context, Long-Term Storage, and Episodic Recall

Reasoning Models Explained: How o1, o3, and DeepSeek R1 Think Before They Answer

LoRA and QLoRA: Fine-Tuning LLMs on a Single GPU

Graph RAG: When Knowledge Graphs Beat Vector Search

LLM Evaluation Pipelines: How to Test What Your Model Actually Does

Semantic Caching for LLMs: Cut Your API Bill by 60%