AI Lookalike Audience Modeling Developer

Krato AI

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

The best customers you have not found yet look like your best customers. Lookalike modeling — building audience segments that share behavioral and demographic signatures with high-value existing customers — is one of the most reliable levers in performance marketing. Done well, it can halve customer acquisition cost. Done poorly, it creates audiences that look similar on paper but behave completely differently in practice. We build growth marketing intelligence for 180 DTC brands. Our lookalike modeling system builds audience seeds from CRM customer data, generates behavioral and firmographic similarity scores against external data sources, and produces audiences that integrate directly with Meta, Google, and programmatic buying platforms. You will own the similarity modeling layer: designing the embedding space that represents customer characteristics, improving the matching quality for cold-start brands with small seed audiences, and building the outcome tracking that measures whether lookalike audiences actually convert at better rates.

Fully remote.

Responsibilities

Build customer embedding models for lookalike audience seed representation
Design similarity scoring against external behavioral and firmographic data sources
Improve matching quality for brands with small seed audiences under 1,000 customers
Implement audience export integrations for Meta, Google, and programmatic platforms
Build conversion outcome tracking to measure lookalike audience quality
Create audience quality scoring that predicts conversion rates before campaign launch

Requirements

3+ years in ML engineering with marketing analytics or audience modeling experience
Experience with embedding models, similarity search, or lookalike modeling systems
Strong Python, SQL, and Spark skills for large-scale audience data processing
Familiarity with digital advertising platforms and audience targeting concepts
Understanding of privacy constraints and data clean room approaches