AI engineer's 14-topic roadmap: RAG, quantization, MCP, inference engines and more

Scobleizer · x · 2026-09-13

An AI engineer with 2 years of experience lists priority topics for breaking into AI engineering: RAG, embeddings & vector DBs, quantization (AWQ/GPTQ/GGUF, FP16/INT8/INT4), RAGAS evaluation, model routing & fallbacks, observability, MCP, agentic patterns, memory & context management, guardrails, inference engines (vLLM/TensorRT/SGLang), load balancing, local vs cloud inference, and backend/system design. The biggest mistake, he says, is focusing only on prompting and calling LLM APIs — AI engineering is about building reliable, scalable systems around models.

Original post →

More from coding & agent

coding & agent channel →