Match Jobs for Product Manager Roles

Job Matching Example

The API provides pre-generated vector embeddings for all job posts, currently created using OpenAI's text-embedding-3-small model. These embeddings capture the semantic meaning of job titles and descriptions, enabling the API to perform semantic searches based on a job profile description.

When you provide a job profile description (e.g., "Experienced in defining product vision, managing roadmaps, and collaborating with cross-functional teams to deliver successful products."), the API:

1. Converts the text into a vector embedding in real-time.
2. Compares this embedding against the pre-generated embeddings of job posts using cosine similarity.
3. Returns job listings that are most semantically similar to the profile, ordered by relevance.

Here's a link to a live API results page (works without an API key for this example):
Experienced in defining product vision, managing roadmaps, and collaborating with cross-functional teams to deliver successful products.

The results include a cosine_dist field, which indicates the similarity between the query and each job post. Lower values represent higher semantic similarity.

Vector search is part of the access pro+ and access ultra plans, with a daily allowance of text-based queries. See the vector embeddings and search docs for all parameters.