InterviewReady/ai-engineering-resources

Curated research papers organized by technical domain—tokenization, vectorization, transformer architectures, mixture-of-experts, RLHF, reasoning mechanisms, and optimization techniques—covering the full ML inference and training stack. Includes foundational work on attention mechanisms, state-space models as transformer alternatives, and inference-time scaling approaches, alongside practical case studies from Meta, Netflix, and Uber demonstrating production LLM systems. Designed as a structured learning path complementing the accompanying video course rather than a standalone implementation.

2,366 stars.