AI Audience Segmentation Model Developer

Talmion Data

Remote · $100k – $130k / year · Full-time · Posted 4 months ago

This role is no longer accepting applications

Don't miss the next role like this

Create a free profile with your skills. We match you to new AI roles as they open, and companies hiring can contact you directly.

Create free profile, 2 minutes

Similar open roles you can apply to now:

See all open AI jobs

This role is no longer accepting applications

Don't miss the next role like this

Create a free profile with your skills. We match you to new AI roles as they open, and companies hiring can contact you directly.

Create free profile, 2 minutes

Similar open roles you can apply to now:

See all open AI jobs

About the role

Our personalization platform segments 18 million users across 60 B2C clients — subscription boxes, streaming apps, e-commerce stores. The audience segments drive every downstream decision: which content to show, which discount to offer, which channel to use. When segments are stale or coarse, every personalization downstream suffers. You'll rebuild our segmentation model stack from the ground up. The current system runs K-means on behavioral features with weekly batch updates. We need something more dynamic: online clustering that updates as users behave, hierarchical segments that support both broad and fine-grained targeting, and a segment quality scoring system that tells clients when their audiences have drifted from their original intent. The data science team is seven people. You'll own this project with a junior analyst supporting you. The output isn't just a model — it's an API and UI component that client success teams use to configure and evaluate audiences without writing code.

Fully remote.

Responsibilities

Redesign the audience segmentation system from batch K-means to dynamic online clustering
Build hierarchical segment structures supporting broad and fine-grained targeting
Develop segment quality scoring to detect audience drift over time
Create APIs that expose segment configuration to client-facing product teams
Design evaluation frameworks measuring segment business impact vs. a baseline
Collaborate with client success teams to translate business targeting needs into model objectives

Requirements

3+ years in ML or data science with customer segmentation or behavioral analytics experience
Strong Python and SQL skills for feature engineering at scale
Experience with clustering algorithms and unsupervised learning techniques
Familiarity with online or streaming ML for real-time model updates
Ability to communicate model design decisions to non-technical stakeholders