Practical AI and machine learning engineering. LLM inference, tokenization, RAG pipelines, model deployment, vector databases, and the infrastructure behind modern AI applications.
6 articles
A practical guide to monitoring LLM applications in production -- input/output logging, cost tracking, quality metrics, and a comparison of LangSmith, Langfuse, and Arize.
End-to-end guide to deploying ML models -- from ONNX export and FastAPI serving to Kubernetes GPU workloads, canary deployments, and Prometheus monitoring.
A practical guide to choosing between prompt engineering and fine-tuning for LLMs -- techniques, costs, LoRA/QLoRA, and a decision framework for production systems.
A practical guide to vector databases -- how embeddings and ANN algorithms work, and an honest comparison of Pinecone, Weaviate, Qdrant, and pgvector.
A practical guide to building Retrieval-Augmented Generation pipelines -- from document chunking and embedding to hybrid retrieval and evaluation metrics.
Language models process tokens, not words. Learn how BPE tokenization works, what the context window really is, and how the KV cache speeds up generation — with real pricing comparisons across OpenAI, Anthropic, and Google.
New articles delivered to your inbox. No spam.