AI Engineering

Hugging Face NLP / LLM Course

Hugging Face's official course on building NLP and LLM applications using the Transformers, Datasets, and Accelerate libraries. Free, comprehensive, and maintained by the team that builds the ecosystem most enterprise AI applications depend on.

Building and Evaluating Advanced RAG Applications

Advanced RAG techniques including sentence-window retrieval, auto-merging retrieval, and evaluation using TruLens. Relevant for engineering teams building enterprise knowledge base applications over regulated-industry document sets.

LLMOps

DeepLearning.AI's short course on operationalizing large language models — covering prompt versioning, evaluation pipelines, fine-tuning, and deployment best practices. Directly applicable to engineering teams building production LLM features.

AI Engineering: Building Applications with Foundation Models

Chip Huyen's guide to building production AI applications using foundation models — covering prompt engineering, RAG, fine-tuning, evaluation, and deployment. The most current technical reference for teams building enterprise LLM applications.

Natural Language Processing with Transformers, Revised Edition

The definitive hands-on guide to building NLP applications with Hugging Face Transformers — from text classification and NER to question answering and generative models. Written by core Hugging Face team members; essential for any AI engineering team.

Building LLMs for Production

A practical guide to taking LLMs from prototype to production — covering evaluation frameworks, safety guardrails, cost optimization, and monitoring. Addresses the specific challenges engineering teams face when deploying AI in compliance-sensitive environments.

Stanford CS25: Transformers United

Stanford's seminar series on transformer architectures featuring leading researchers from Google, OpenAI, DeepMind, and academia. Covers attention mechanisms, scaling laws, fine-tuning, and applications — the academic frontier made accessible.

Google DeepMind Research Talks

Google DeepMind's official channel covering frontier AI research — AlphaFold, Gemini architecture, reinforcement learning, and safety research. Authoritative source for engineering teams tracking the state of the art in foundation model development.

Let's Build GPT: From Scratch, in Code, Spelled Out

Karpathy builds a GPT transformer from scratch in pure Python — following the 'Attention Is All You Need' paper. The most influential technical video in the AI engineering community; essential for any engineer who wants to understand LLMs at the implementation level.

Introducing SimpleQA

Fast-tracking genetic leads to reverse cellular aging

OpenAI Platform

OpenAI's API platform for GPT-4, embeddings, and fine-tuning — the most widely integrated LLM API in enterprise software. Provides the baseline capability benchmark against which all other LLM integrations are measured.

Hugging Face Hub

The largest repository of open-source AI models, datasets, and demos — with 500,000+ models available for download and fine-tuning. The primary resource for AI engineering teams evaluating, adapting, and deploying open-weight models in enterprise environments.

LangSmith

LangChain's observability and evaluation platform for LLM applications — providing tracing, performance monitoring, cost tracking, and automated evaluation. Essential for AI engineering teams that need to debug, measure, and improve production LLM systems.