Phase 17

Infrastructure And Production

Ship AI to the real world. Scale, monitor, optimize.

01Managed LLM Platforms — Bedrock, Vertex AI, Azure OpenAILearn~60 minutesQuiz 02Inference Platform Economics — Fireworks, Together, Baseten, Modal, Replicate, AnyscaleLearn~60 minutesQuiz 03GPU Autoscaling on Kubernetes — Karpenter, KAI Scheduler, Gang SchedulingLearn~75 minutesQuiz 04Serving Engine Internals — PagedAttention, Continuous Batching, Chunked PrefillLearn~75 minutesQuiz 05EAGLE-3 Speculative Decoding in ProductionLearn~60 minutesQuiz 06Prefix-Cache Serving — RadixAttention and KV ReuseLearn~75 minutesQuiz 07Hardware-Specialized Inference Compilation — FP8 and NVFP4 on BlackwellLearn~75 minutesQuiz 08Inference Metrics — TTFT, TPOT, ITL, Goodput, P99Learn~60 minutesQuiz 09Production Quantization — AWQ, GPTQ, GGUF K-quants, FP8, MXFP4/NVFP4Learn~75 minutesQuiz 10Cold Start Mitigation for Serverless LLMsLearn~60 minutesQuiz 11Multi-Region LLM Serving and KV Cache LocalityLearn~60 minutesQuiz 12Edge Inference — Apple Neural Engine, Qualcomm Hexagon, WebGPU/WebLLM, JetsonLearn~60 minutesQuiz 13LLM Observability Stack SelectionLearn~60 minutesQuiz 14Prompt Caching and Semantic Caching EconomicsLearn~60 minutesQuiz 15Batch APIs — the 50% Discount as Industry StandardLearn~45 minutesQuiz 16Model Routing as a Cost-Reduction PrimitiveLearn~60 minutesQuiz 17Disaggregated Prefill/Decode — NVIDIA Dynamo and llm-dLearn~75 minutesQuiz 18Production Serving Stack — KV Offloading and Cache-Aware RoutingLearn~60 minutesQuiz 19AI Gateways — LiteLLM, Portkey, Kong AI Gateway, BifrostLearn~60 minutesQuiz 20Shadow Traffic, Canary Rollout, and Progressive Deployment for LLMsLearn~60 minutesQuiz 21A/B Testing LLM Features — GrowthBook, Statsig, and the Vibes ProblemLearn~60 minutesQuiz 22Load Testing LLM APIs — Why k6 and Locust LieBuild~75 minutesQuiz 23SRE for AI — Multi-Agent Incident Response, Runbooks, Predictive DetectionLearn~60 minutesQuiz 24Chaos Engineering for LLM ProductionLearn~60 minutesQuiz 25Security — Secrets, API Key Rotation, Audit Logs, GuardrailsLearn~60 minutesQuiz 26Compliance — SOC 2, HIPAA, GDPR, PCI-DSS, EU AI Act, ISO 42001Learn~60 minutesQuiz 27FinOps for LLMs — Unit Economics and Multi-Tenant AttributionLearn~60 minutesQuiz 28Self-Hosted Serving Selection — Matching Engine to Hardware and ScaleLearn~45 minutesQuiz 29Model Demo Interfaces — From a Function to a Shareable AppBuild~90 minutesQuiz 30GPU Architecture and the Execution ModelBuild~60 minutesQuiz 31Kernel Fusion, Triton, and the Profiling WorkflowBuild~75 minutesQuiz 32FlashAttention-2 from Scratch: Tiled Online SoftmaxBuild~75 minutesQuiz

“Stay hungry, stay foolish.”

— Steve Jobs