AI Compute, Inference & Performance Engineering
Not Started0 / 10 complete
Open a video or resource link, watch it, then check its box to track your progress and unlock what comes next.
10 lessons3 levels1 capstone project
Engineer the AI performance envelope across GPU memory, batching, KV cache, quantization, parallelism, model serving, throughput, latency, capacity and cost; benchmark and tune production inference systems.
BASIC
- Mastering LLM Inference Optimization — AI Engineer (60 min selected)
Deep production view of GPUs, KV cache, tensor parallelism, quantization, batching, latency and deployment cost. - LLM Inference Optimization Explained (35 min selected)
Compact walkthrough of prefill/decode, continuous batching, KV cache, quantization and profiling. - What Is MLOps? — IBM Technology (8 min)
Places serving, repeatability, monitoring and operations around model performance.
INTERMEDIATE
- Machine Learning Explained: A Guide to ML, AI & Deep Learning — IBM Technology
Apply AI Compute, Inference & Performance Engineering through the adjacent capability: ML Foundations & GenAI. - AI Red Teaming 101: Full Course — Microsoft Developer
Apply AI Compute, Inference & Performance Engineering through the adjacent capability: AI Red Teaming & Adversarial Testing. - The Art of SLOs — Google
Apply AI Compute, Inference & Performance Engineering through the adjacent capability: Production Backend & Agentic Systems Engineering.
ADVANCED
- Let's Build GPT From Scratch — Andrej Karpathy
Extend AI Compute, Inference & Performance Engineering into senior/production practice through ML Foundations & GenAI. - AI Infrastructure on Kubernetes: Run:ai & KAITO — Microsoft / NVIDIA
Extend AI Compute, Inference & Performance Engineering into senior/production practice through AI Factory. - MCP Workshop — Anthropic
Extend AI Compute, Inference & Performance Engineering into senior/production practice through AI Agents.