Select and operate model runtimes, routing patterns, hardware profiles, capacity controls, and reliability targets.
Learning outcomes
Curriculum
The chapters are individually addressable documentation pages. You can link directly to a concept from another program, architecture decision, or implementation guide.
Connect workload requirements to runtime and deployment boundaries.
Translate workload behavior into governed runtime, endpoint, routing, hardware, and service requirements.
Compare public cloud, private cloud, on-premises, hybrid, edge, restricted-network, and air-gapped patterns without treating one as automatically sovereign.
Inventory the data, models, prompts, artifacts, identities, tools, interfaces, infrastructure, and evidence that require protection.
Design governed endpoints, routing policy, capacity envelopes, and hardware placement.
Separate model runtime, API contract, policy enforcement, scheduling, and workload responsibilities.
Design routing and hardware profiles from measured workload envelopes, isolation needs, and failure behavior.
Define release, degradation, recovery, observability, and controlled-change behavior.
Operate model endpoints with explicit access, degradation, recovery, telemetry, and change controls.
Turn acceptance criteria into repeatable promotion decisions with recorded evidence and rollback conditions.
Define capacity envelopes, degradation behavior, service objectives, recovery targets, and tested restoration evidence.
Design signals that explain service health, AI behavior, policy outcomes, change, and incidents without leaking sensitive content.
Version complete AI behavior, assess change impact, approve promotion, support rollback, and retire superseded assets.
Record the runtime decision and demonstrate it against measured requirements.
Record context, options, control consequences, evidence, dependencies, limitations, and reversal triggers for material decisions.
Create and test a runtime decision for a defined private AI workload.
Verify runtime, routing, hardware, reliability, evaluation, security, and operational decisions.
Measure a runtime profile and design governed routing, capacity, and recovery.
Design exercise; executable implementation pending
This curriculum does not certify a runtime, accelerator, benchmark result, or production capacity. Fast-changing runtime commands and hardware compatibility belong in separately tested adapters with explicit versions and measurement conditions.