Perivitta Rajendran

May 12, 2026

Neuromorphic Chips: The Brain-Inspired Hardware That Could Replace GPUs

GPUs brute-force intelligence with matrix math. Neuromorphic chips take the opposite approach, mimicking how biological neurons fire and wire to achieve AI...

blogpost· 21 mins read

Mar 27, 2026

blogpost

Multi-Agent Systems: Orchestration, Communication, and Collaborative AI

A single agent hits context and capability limits fast. Multi-agent systems distribute work across specialized roles with structured communication protocols. Orchestration patterns...

blogpost· 16 mins read

Mar 25, 2026

blogpost

LLM Inference Optimization: Quantization, KV Cache, and Serving at Scale

Serving a 70B model cheaply requires quantization, KV cache tuning, continuous batching, and the right serving stack. A systems-level breakdown of vLLM,...

blogpost· 27 mins read

Mar 22, 2026

blogpost

Embedding Models: Training, Fine-Tuning, and Optimization for Retrieval

Embedding quality determines what your retrieval system can find. How contrastive training works, when to fine-tune versus use off-the-shelf models, and what...

blogpost· 28 mins read

Mar 21, 2026

blogpost

Advanced Prompt Engineering: Chain-of-Thought, ReAct, and Tree-of-Thoughts Explained

Chain-of-thought improves multi-step reasoning. ReAct adds tool use. Tree-of-thoughts explores multiple solution paths. When each technique earns its token cost — and...

blogpost· 24 mins read

Mar 19, 2026

blogpost

Structured Outputs in LLMs: JSON Mode, Function Calling, and Schema Validation

Free-form LLM output breaks parsing pipelines. JSON mode, function calling, grammar-constrained decoding, and Pydantic validation are the layers that make structured output...

blogpost· 20 mins read

Mar 14, 2026

blogpost

Prompt Injection Attacks: How LLMs Get Exploited and How to Defend Your Application

Prompt injection turns user input into an instruction override. Indirect injection, jailbreaks, and data exfiltration vectors are all in scope — and...

blogpost· 23 mins read

Mar 12, 2026

blogpost

LLM Observability: Tracing, Logging, and Debugging AI Applications

You can't debug what you can't trace. Setting up prompt logging, span tracing, cost tracking, and latency monitoring for production LLM apps...

blogpost· 19 mins read

Mar 5, 2026

blogpost

Hybrid Search: Combining Keyword and Vector Search for Better Retrieval

Pure vector search misses exact matches. BM25 misses semantic intent. Reciprocal rank fusion combines both without the tuning overhead of learned fusion...

blogpost· 19 mins read

Feb 27, 2026

blogpost

PEFT Methods Explained: LoRA, QLoRA, and Adapter-Based Fine-Tuning

Full fine-tuning a 7B model costs thousands in GPU hours. LoRA and QLoRA achieve comparable quality by training a fraction of the...

blogpost· 21 mins read

Perivitta Rajendran

Recent writing

Random Forest: A Complete Beginner's Guide

Synthetic Data: How AI Trains Itself on AI-Generated Data

AI for Drug Discovery: How AlphaFold Reinvented Biology

From the archive

Neuromorphic Chips: The Brain-Inspired Hardware That Could Replace GPUs

Multi-Agent Systems: Orchestration, Communication, and Collaborative AI

LLM Inference Optimization: Quantization, KV Cache, and Serving at Scale

Embedding Models: Training, Fine-Tuning, and Optimization for Retrieval

Advanced Prompt Engineering: Chain-of-Thought, ReAct, and Tree-of-Thoughts Explained

Structured Outputs in LLMs: JSON Mode, Function Calling, and Schema Validation

Prompt Injection Attacks: How LLMs Get Exploited and How to Defend Your Application

LLM Observability: Tracing, Logging, and Debugging AI Applications

Hybrid Search: Combining Keyword and Vector Search for Better Retrieval

PEFT Methods Explained: LoRA, QLoRA, and Adapter-Based Fine-Tuning

Recent writing

Random Forest: A Complete Beginner's Guide

Synthetic Data: How AI Trains Itself on AI-Generated Data

AI for Drug Discovery: How AlphaFold Reinvented Biology

Not sure where to start? Just ask.

From the archive

Neuromorphic Chips: The Brain-Inspired Hardware That Could Replace GPUs

Multi-Agent Systems: Orchestration, Communication, and Collaborative AI

LLM Inference Optimization: Quantization, KV Cache, and Serving at Scale

Embedding Models: Training, Fine-Tuning, and Optimization for Retrieval

Advanced Prompt Engineering: Chain-of-Thought, ReAct, and Tree-of-Thoughts Explained

Structured Outputs in LLMs: JSON Mode, Function Calling, and Schema Validation

Prompt Injection Attacks: How LLMs Get Exploited and How to Defend Your Application

LLM Observability: Tracing, Logging, and Debugging AI Applications

Hybrid Search: Combining Keyword and Vector Search for Better Retrieval

PEFT Methods Explained: LoRA, QLoRA, and Adapter-Based Fine-Tuning