LLM Inference Engineering: Theory, Practicals and Research

This AI product management training focuses on the technical foundations behind large language model inference, deployment, and performance tradeoffs. The course develops capability in understanding inference workflows, evaluating system constraints, and reasoning about latency, cost, reliability, and scaling decisions for AI-enabled products. It applies in real product work where PMs collaborate with engineering teams on infrastructure choices, product performance, experimentation, and measurable outcomes tied to AI system behavior. Best suited for technical PMs, AI product leaders, and builders who want deeper operational understanding of modern AI systems beyond surface-level prompting workflows.