Natural language, similar-jobs and resume queries with filters: one API, one embedding model, 4M+ live listings sourced directly from company career pages.
QUERY (NATURAL LANGUAGE)
"senior backend engineer building distributed payment systems with Go and Kafka, remote-friendly EU"
SOCRATES V2 EMBEDDING · 768 DIMENSIONS
[-0.0294, 0.0613, -0.0413, 0.0187, -0.0822, 0.0154, ...762 more]
Senior Payment Platform Engineer
Klarna · Stockholm · Remote EU
Staff Engineer, Money Movement
Wise · London · Hybrid
Senior Software Engineer, Payments Infrastructure
Adyen · Amsterdam · Hybrid
More-like-this, natural language with filters, or raw vector input — all through Neural Search, backed by the socrates v2 index.
Pass reference job IDs under vector.job_ids, or an uploaded resume's artifact ID under vector.artifact_id. Get the most similar live listings, ranked by meaning.
Send a natural language query under vector and structured filters under lexical — location, salary, experience, industry, posting date. Combined ranking, single round trip.
Pass raw 768-dim vectors to Neural Search via vector.vectors. Skip re-encoding when you've cached embeddings from our resume embed endpoint in your own pipeline.
What the Semantic Search API actually powers in production.
Let users type "remote backend role at a Series B fintech with equity" instead of clicking through filters. The API matches role, seniority, company stage, geography, and compensation as a single query.
Pass a job ID, get the most similar live listings. ML engineer roles cluster with Applied Researcher; data scientist clusters with quant analyst. Powers detail-page rails and "you might also like" feeds.
Feed user intent — natural language goals, conversation context, scraped requirements — directly to the API. Match user descriptions to live listings without prompt engineering against keywords.
"ML engineer" should match Applied Researcher AND filter to remote, $150k+, senior, posted in the last 30 days. Neural Search runs both in one request with combined ranking.
Cache vectors once, query them many times. Match cached user-intent vectors against fresh job postings every hour without re-encoding. Powers batch matching, scheduled job alerts, and custom recommender stacks.
A free API key includes 500 jobs a month across every search endpoint. Prototype before you pay.
Works with any HTTP client. Official Python SDK — pip install hirebase.
Results are ranked by similarity. Pass vector.score_threshold (0.0 - 1.0) on Neural Search to drop low-quality matches.
# Filtered semantic search in one request
curl -X POST https://api.hirebase.org/v2/jobs/neural-search \
-H "Content-Type: application/json" \
-H "x-api-key: YOUR_API_KEY" \
-d '{
"vector": {
"query": "senior backend engineer building
distributed systems with Go and Kafka"
},
"lexical": {
"location_types": ["Remote", "Hybrid"],
"experience": ["Senior"],
"industry": "Tech, Software & IT Services",
"days_ago": 30,
"limit": 10
}
}'# Returns ranked results with similarity scores
{
"jobs": [
{
"_id": "6814bw99fc2284gt4777f21a",
"job_title": "Senior Payment Platform Engineer",
"company_name": "Klarna",
"location_type": "Remote",
"experience_level": "Senior",
"date_posted": "2026-04-15"
}, ...
],
"total_count": 847,
"total_pages": 85
}Domain-tuned embeddings preserve role, seniority, function, and skill-level distinctions that general-purpose models flatten.
[ 01 ] Embedding model
Proprietary 768-dimensional model trained on tens of millions of job postings. Model name and version returned on every embedding response so you can pin to a specific release.
[ 02 ] Similarity scoring
Results come back ordered by cosine similarity to your query. Pass `vector.score_threshold` (0.0–1.0) to drop weak matches.
[ 03 ] Three input modes
Neural Search takes natural language under vector.query (encoded server-side), reference jobs under vector.job_ids, a resume artifact_id, or raw 768-dimensional vectors under vector.vectors.
[ 04 ] Hybrid ranking
Add lexical filters next to the vector: titles, location, salary, experience, industry, days_ago and more. Results are ranked by semantic score, then lexical rank.
[ 05 ] Pagination
The ranking is computed on the first page and reused for 15 minutes, so later pages of the same query stay consistent with page 1.
[ 06 ] Free plan
Every request needs an API key. The Free plan includes 500 jobs a month across every search endpoint, so you can prototype Neural Search before paying.
Richer prompts give the embedding model more dimensions to match against. A well-written query consistently outperforms structured filters alone.
Don't relegate context to filter parameters when the embedding model can match it from the query itself.
Stage, size, and industry character match through the company entity linkage on every job.
For agent and copilot workflows, give the model both the candidate's current state and their target.
The query ranks by meaning; filters are what actually narrow results. For 30-day windows, salary floors, industry, or location, send Neural Search both vector and lexical blocks.
vs. building it yourself with general-purpose embeddings and a vector DB, or buying keyword-only job posting feeds.
Free API key, no card. Run a real semantic search in your terminal in 60 seconds.
