Production Backend & Agentic Systems Engineering
Open a video or resource link, watch it, then check its box to track your progress and unlock what comes next.
Build and operate reliable backend and long-running agent systems where uptime, correctness, durable state and recovery matter.
- The Art of SLOs — Google (3:27)
Defines reliability targets and error budgets before designing for uptime. - Raft — Martin Kleppmann (38 min)
Builds intuition for correctness under node and network failure. - Multi-Agent Swarms with LangGraph — LangChain (10 min)
Quick hands-on view of stateful, multi-step agent orchestration.
- The AI Factory (Jensen Huang) — NVIDIA
Apply Production Backend & Agentic Systems Engineering through the adjacent capability: AI Factory. - Scale AI with an AI Factory — Red Hat + NVIDIA
Apply Production Backend & Agentic Systems Engineering through the adjacent capability: AI Factory. - AI Red Teaming 101: Full Course — Microsoft Developer
Apply Production Backend & Agentic Systems Engineering through the adjacent capability: AI Red Teaming & Adversarial Testing.
- AI Infrastructure on Kubernetes: Run:ai & KAITO — Microsoft / NVIDIA
Extend Production Backend & Agentic Systems Engineering into senior/production practice through AI Factory. - Let's Build GPT From Scratch — Andrej Karpathy
Extend Production Backend & Agentic Systems Engineering into senior/production practice through ML Foundations & GenAI. - MCP Workshop — Anthropic
Extend Production Backend & Agentic Systems Engineering into senior/production practice through AI Agents.