AI product engineering

Turning creator metrics into personalized recommendations.

Experience snapshot
Led in a previous engineering leadership role
LLM systems / Data pipelines / Web + mobile
Blue glass layers with a green path
01
Prior-role exampleCreator recommendations

01 / The constraint

Creators could see views, reach, and engagement for each post, but no system turned those signals into a next step.

02 / The system

We normalized content metadata and performance signals, ran them through model-backed services, and delivered specific guidance in the existing web and mobile product.

03 / The change

Creators received consistent recommendations instead of reading several dashboards. The system also supported more recommendation types and feedback loops.

What this demonstrates

The system turned model output into a recommendation inside the product instead of another dashboard to interpret.

Have a related problem?

Define the first system to ship.

Tell us what people do today, where the process breaks, and what a better outcome would change for the business.

Discuss a related system (opens in a new tab)