Portfolio/Tracks/Building Production LLM Systems

Building Production LLM Systems

Taking an LLM from a model call to a real system — retrieval, agentic tool use, inference optimization, and evaluation.

Progress0/5 complete

1

Embeddings & Vector Search: The Foundation of Semantic AI

2

Building a Production RAG Pipeline from Scratch

3

LLM Agents: Tool Use, Planning & Autonomous Reasoning

4

LLM Inference: KV Cache, Speculative Decoding & Batching

5

Evaluating LLMs: Benchmarks, Metrics & Real-World Testing