Junior AI Data Discovery Recommendation Developer

Lyrex Data

Remote · $60k – $80k / 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

Data catalogs store metadata about available datasets. They don't tell you which datasets you should care about for your current analytical project. A data analyst working on customer churn analysis shouldn't have to browse 10,000 catalog entries to discover which tables contain the subscription event history, the customer attribute data, and the support interaction records that are most relevant to their work. Our data catalog platform serves 65 enterprise clients with 4.8 million cataloged datasets. Data discovery recommendation — proactively surfacing relevant datasets based on the user's current query context, role, team membership, and usage patterns — is the feature that transforms the catalog from a passive registry into an active analytical assistant. You'll help build it. As a junior developer, you'll implement the usage-based recommendation signals: tracking which datasets are frequently used together, which are accessed after specific types of search queries, and which are used by data analysts working on similar problems. Senior engineers design the recommendation architecture; you build the usage signal pipelines and the recommendation serving layer that puts relevant suggestions in front of users at the right moment.

Fully remote.

Responsibilities

Build dataset usage signal tracking: co-access patterns, search-to-access sequences, and team usage patterns
Implement collaborative filtering recommendations surfacing datasets frequently used together
Create query-context recommendation matching analyst search intent to relevant uncatalogued tables
Develop freshness and quality signals weighting recommendations toward actively maintained datasets
Build recommendation serving API delivering context-aware suggestions in the catalog search interface
Track recommendation click-through and adoption rates as primary quality metrics

Requirements

1+ year of Python and SQL development experience
Basic familiarity with recommendation systems or data pipeline development
Interest in data catalog products, analytics engineering, or developer tooling
Attention to recommendation relevance and signal accuracy
Good communication for collaborating with senior engineers on recommendation system design