AI Systems Performance Engineering
A 1,062-page O’Reilly field guide and active open source lab for GPU architecture, CUDA, PyTorch, distributed training, and modern inference serving.
1.7K+ GitHub stars · 2,700+ commits
Hi, I’m
Chris Fregly
AI systems performance engineer · Product leader · Founder · Advisor · 3× O’Reilly author
I build and explain high-performance AI systems. My work spans GPU kernels, distributed training, high-throughput inference, and the product systems that move AI into production.
1,062pages in the 2025 book
1.7K+GitHub stars
440K+course enrollments
100K+community members worldwide
780K+YouTube views
Recent work
Systems depth, packaged for builders
The current work connects low-level performance engineering with the product discipline needed to ship useful AI.
Agent Harness Optimization
An evidence-first workbench for evaluating agent prompts, tools, transcripts, and traces without losing the receipts behind each conclusion.
Prompts · Traces · Evals · Evidence
GPU Performance Tuning
A set of agent workflows for profiling and improving GPU inference, including benchmarking, quantization, speculative decoding, and performance reports.
32 focused workflows
Books
Three O’Reilly books across the AI stack
From production data science to generative AI and the performance of the full system beneath it.
AI Systems Performance Engineering
Optimize training and inference across GPU hardware, CUDA kernels, compilers, PyTorch, networking, storage, and multinode systems.
Generative AI on AWS
Build context-aware multimodal applications with foundation models, fine-tuning, reinforcement learning, RAG, and production deployment patterns.
Data Science on AWS
Implement end-to-end machine learning pipelines with data engineering, model training, tuning, and production deployment on AWS.
Course
Generative AI with Large Language Models
A practical course built with DeepLearning.AI and AWS for people who want to understand the full generative AI lifecycle.
Learn the full generative AI lifecycle
The course covers transformers, model selection, scaling laws, fine-tuning, evaluation, reinforcement learning, inference, and deployment. It includes 47 lessons and three graded assignments.
- 440K+enrollments
- 4.8learner rating
- 24languages
Talks and media
Recent conversations from kernels to clusters
Talks, interviews, and technical sessions from the last two years.
AI Performance Engineering
Hacking AI Accelerators
A systems-level look at the hardware and software choices that shape AI performance.
Watch or listenNVIDIA GTC recap
Performance Highlights from GTC 2026
Recent advances in inference, disaggregated prefill and decode, and the systems work behind faster models.
Watch or listenSuperDataScience · Episode 973
AI Systems Performance Engineering
A conversation about GPU computing, full-stack profiling, and what engineers need to understand beneath modern AI frameworks.
Watch or listenMLOps Community · Episode 363
Software and Hardware Codesign
How PyTorch, CUDA, and NVIDIA GPUs fit together when performance and cost matter in production.
Watch or listenAI Performance Engineering
Dynamic Inference Tuning with CUDA and vLLM
Practical techniques for adapting inference systems as request patterns, memory pressure, and latency targets change.
Watch or listenO’Reilly AI Superstream
High-Performance Agentic AI Inference Systems
Performance patterns for agentic workloads using DeepSeek, NVIDIA Dynamo, vLLM, CUDA, and PyTorch.
Watch or listenCommunity
AI performance is a team sport
I cohost monthly technical sessions with Antje Barth for engineers who build the systems behind modern AI. Our global network reaches more than 100,000 people worldwide. The flagship Meetup group has hosted 375 past events, and the YouTube channel has 193 videos with more than 780,000 views.
100K+worldwide members
375past events
193videos
780K+views