How LinkedIn Unified AI Products Around a Target Audience Graph

Understand how a shared "target audience" representation solves cold-start, decay, and thin-market problems in recommendation systems, and why unifying AI infrastructure often requires unifying teams first.

4 sections ยท 9 lessons

Course outline

The Fragmentation Problem

  1. Why fragmented products often mirror fragmented org charts
  2. The cost of shipping parallel AI features instead of shared foundations

Building a Target Audience Graph

  1. Cold start: inferring audience with LLMs
  2. Warm signals: time-decayed activity weighting
  3. Thin markets: fusing buyer-side and seller-side signals

AI Features Built on a Shared Foundation

  1. Embedding retrieval + multi-stage ranking
  2. Two-stage LLM pipelines for cost-efficient scale

The Organizational Lesson

  1. Design around the customer problem, not the org chart
  2. Why reusable foundations compound over future products

Start learning with Wondering