107. Design an ML Model Serving and Deployment Platform

The brief

Design an ML Model Serving and Deployment Platform. From registry to traffic for hundreds of models: gates, shadow and canary with automatic rollback, packed CPU and GPU pools, LLM serving, cells and audit. Work from the scoping questions below. State assumptions for any unspecified load, guarantee or target, then trace your design end to end. Explain one difficult case and a credible alternative; the worked example is a reference, not a required implementation.

• Set the scope: What runs on it? Traffic and latency?
• Define the contract: Which modes? How fast must a bad version leave?
• Test the boundaries: Who supplies features? Deploy rate? A/B tests?

Constraints

Explicit scope and guarantees

Resolve the scoping questions for an ML Model Serving and Deployment Platform. Separate stated behavior from assumptions, and identify what is outside your design.

Supported operating targets

Declare relevant volume, latency, freshness, quality or cost targets with units. Show calculations or an evaluation plan that can test them; unspecified targets are your assumptions, not hidden pass criteria.

Failure and boundary behavior

Explain how your guarantees hold in a difficult case relevant to this subject. Address: Deploy rate? A/B tests?

What to cover

1. 01

   Scope and behavior contract

   Identify users, required behavior and exclusions. Answer: What runs on it? Traffic and latency?

2. 02

   State and interfaces

   Define the information owned by the system and the inputs, outputs and errors at its boundaries. Resolve: Which modes? How fast must a bad version leave?

3. 03

   Capacity and operating targets

   Estimate the dominant workload and resource demand with units and explicit assumptions. For a learned system, also state how quality is measured and what data is available.

4. 04

   Architecture and central flow

   Draw or describe the responsibilities needed for an ML Model Serving and Deployment Platform. Trace a representative request, event or job from its input to a visible result; identify durable state owners.

5. 05

   Failure and boundary walkthrough

   Walk through a difficult case step by step, including detection and recovery. Consider: Who supplies features? Deploy rate? A/B tests?

6. 06

   Tradeoffs and operations

   Compare a credible alternative using your chosen workload and guarantees. Explain a remaining risk, a signal to watch and when you would change the design.

Worked designs

Explore the architecture and decisions, then build on an example with Coach.

Official design

Design an ML Model Serving and Deployment Platform

From registry to traffic for hundreds of models: gates, shadow and canary with automatic rollback, packed CPU and GPU pools, LLM serving, cells and audit: one-hour boards for junior, senior and staff, with the theory behind them.

Explore the design

Review rubric

AI feedback uses these criteria. Scores are practice feedback.