top of page

articles and knowledge
Search


GPU Kernel Engineering for LLM Inference Review: CUDA, Triton and Flash Attention for Faster AI Serving
A focused guide from the AI Infrastructure, Hardware & Compiler Engineering Series on writing and optimizing GPU kernels for LLM inference with CUDA, Triton and Flash Attention. Available on Kindle and in paperback.

Choochai Thianthae
2 days ago4 min read


Production AI Engineering Series Guide: 21 Books from LLM Pre-Training to Agents, LLMOps and AI Safety
Twenty-one production AI engineering books from ChatVariety Team — pre-training, fine-tuning, inference, RAG, multimodal, agents, MCP, LLMOps, security and safety — with a recommended reading order and Kindle and paperback links.

Choochai Thianthae
Nov 136 min read


Evals That Don't Lie Review: Build LLM Evaluation Pipelines You Can Actually Trust
A practical engineering guide from the Applied LLM Engineering Series on trustworthy LLM evaluation: golden datasets, LLM judges and regression gates. Available on Kindle and in paperback.

Choochai Thianthae
Nov 94 min read


Orchestrating Many Minds Review: Supervisors, Swarms & Handoffs
Our review of Orchestrating Many Minds by ChatVariety Team: proven multi-agent design patterns with supervisors, swarms and handoffs. Available on Kindle and paperback.

Choochai Thianthae
Nov 84 min read


Context Engineering in Practice Review: Better Answers Start With Better Context
Our review of Context Engineering in Practice by ChatVariety Team: context windows, memory architectures and retrieval strategy for LLM apps. On Kindle and paperback.

Choochai Thianthae
Nov 74 min read
bottom of page



