About Canaria

What Canaria is

Canaria turns raw job postings into research-grade intelligence. The platform aggregates 1B+ deduplicated US job postings from Indeed, LinkedIn, and 200,000+ employer career portals, then enriches every record with 100+ structured fields: occupation and industry classification, salary prediction, a 40,000+-skill taxonomy, seniority, work mode, and a per-field confidence score.

We sit between expensive enterprise providers and raw, unenriched data vendors: comparable enrichment depth at a fraction of the price, with the transparency that quant funds, HR tech platforms, enterprise workforce teams, and academic researchers need to trust the data. Coverage is United States primary, 2022-present.

Who builds it

Canaria is built by a small team of ML engineers from Google, Meta, and Amazon, with alumni of Stanford, Caltech, and Columbia. The team ships every layer of the stack, from the scraping infrastructure through the enrichment pipeline to the delivery layer. Methodology, accuracy benchmarks, and known limitations are published openly so buyers can evaluate the data before they commit.

For research and data inquiries, contact our Director of Insights at contact@decanaria.com.

Cite our data

Using Canaria data in a paper, report, or model card? Please cite the dataset using one of the formats below.

Explore further