Chip Huyen
Author, Designing Machine Learning Systems | AI Engineer & Systems Educator
Verified Proof of Work Artifacts
2 items catalogedEach artifact below represents an authenticated research publication, production code repository, or technical architectural framework directly authored or co-created by Chip Huyen. Every entry undergoes editorial source verification.
Evaluation Patterns for LLM Systems in Production
A definitive technical analysis by Chip Huyen breaking down model-graded evals, reference-based vs. reference-free metrics, human evaluation calibration, and online production monitoring loops.
LLM-as-a-judge approaches have inherent biases (length bias, self-enhancement bias) requiring continuous calibration against human golden datasets.
Building LLM-Based Systems: Latency, Cost, and Architecture Trade-offs
Comprehensive guide detailing the engineering differences between training, fine-tuning, and prompt-based RAG architectures in enterprise production.
System design blueprint; implementation performance depends on team infrastructure and latency budgets.