AI Job Search - Semantic Search by Meaning, Not Keywords

Describe the job you want in plain English and get back the best-matching live jobs, ranked by meaning - not by which postings happen to repeat your keywords. Semantic AI search over 4,000,000+ jobs scraped directly from company career pages, with expired and ghost jobs filtered out. Powered by Hirebase.

Keyword search only finds the words you spell. A search for registered nurse skips the hospital that posts "RN - Trauma ICU"; this actor understands they mean the same thing - in the example below, 34 of the 300 results are titled only "RN", and a keyword search would have missed every one.

Why this actor?

• 🧠 Search by meaning - write the query the way you'd brief a recruiter: "senior backend engineer building payment systems in Go at a fintech".
• 🏆 Ranked results - every job carries a rank, 1 = closest match, so the first rows are the ones to read.
• 🎯 Semantic + filters in one run - combine the query with remote/hybrid, location and radius, salary, experience, industry, company size and more.
• 🚫 No expired or ghost jobs - listings come straight from employer career pages and are removed when they go offline.
• ♻️ Duplicates dropped before you pay - the same role posted in ten cities is saved once by default.

How to use it

1. Type what you're looking for into What job are you looking for?
2. Optionally narrow it down: workplace type, locations, experience level, salary, industry, posted date.
3. Set Max results (up to 2,500) and run.

Results come back best match first. To keep only close matches, set Minimum match strength - around 60% keeps most relevant jobs, 65-70% keeps only the closest few, and 75% or more usually returns nothing.

Example input

{
  "query": "registered nurse in an ICU night shift",
  "locationTypes": ["In-Person"],
  "maxResults": 300
}

Output

A real result from the query above (run 2026-09-22; rankings move day to day as postings open and close):

{
  "rank": 1,
  "jobTitle": "Registered Nurse (RN) - ICU Nights PRN",
  "companyName": "Community Health Systems",
  "companyWebsite": "https://chs.net",
  "applicationLink": "https://fa-evxo-saasfaprod1.fa.ocs.oraclecloud.com/hcmUI/CandidateExperience/en/sites/CX_1/job/161707",
  "datePosted": "2026-09-22",
  "locationType": "In-Person",
  "location": "Vicksburg, MS, United States",
  "jobType": "Full Time",
  "jobCategories": ["Healthcare Services Jobs"],
  "yearsOfExperience": { "min": 0, "max": 2 },
  "salaryRange": null,
  "requirementsSummary": "The RN must have 0-2 years of experience in a clinical nursing role or student clinical rotations in an acute care setting and hold a valid RN license",
  "visaSponsored": false,
  "jobBoard": "oraclecloud",
  "jobSlug": "registered-nurse-rn-icu-nights-prn-84c57924",
  "companySlug": "community-health-systems"
}

The rest of the top five were ICU nursing roles at Wellstar, Tenet and University Hospitals. At #11 and #12 came RN - Trauma ICU (Carilion Clinic) and RN - Neonatal ICU Nights (UT Southwestern) - neither title contains "registered nurse", so a keyword search would have missed both.

Each result also includes company logo, structured locations, skills, education level, recruiting-agency flag, company profile data, quality scores, a cleaned text description and the original HTML. Export to JSON, CSV or Excel, or pipe into Make, n8n, Zapier, Google Sheets or the Apify API.

Great for

• Job seekers and career tools - "find me roles like this one" without guessing every title variant.
• Recruiters and sourcers - map a hard-to-name role ("founding engineer who has shipped developer tools") across every employer hiring for it.
• Job boards and newsletters - build curated, on-theme lists from a single description.
• AI agents - hand an LLM's natural-language request straight to the search.

Pricing

Pay per result - you are only charged for jobs actually saved, up to 2,500 results per run. Duplicates skipped by the dedupe setting are never charged.

FAQ

Do I need an API key? No - API access is built into the actor. Describe the job and run.

How is this different from the Job Search Scraper? The Job Search Scraper matches exact keywords and titles and can page through millions of results - use it when you know the precise words or want complete coverage of a filter. This actor ranks by meaning and returns the most relevant 2,500 - use it when the right jobs are described in many different ways.

Why is it capped at 2,500 results? Semantic search is a relevance ranking: it returns the closest 2,500 matches for your query. Past that point results are rarely relevant. For bulk exports of everything matching a filter, use the Job Search Scraper.

Is there a relevance score? Results are returned in relevance order and numbered with rank. A numeric similarity score is not exposed - use Minimum match strength to cut off weak matches instead.

Which filters work with AI search? Workplace type, locations and radius, employment type, experience level, years of experience, posted date, ATS platform, industry (one at a time), company name and size, recruiting agencies, salary and visa sponsorship - each checked against live results. Job categories and sub-industries are not supported by AI search: put them in the query instead ("data analyst at a fintech"). Sorting is not offered - results are always ordered by match.

Can I run it on a schedule? Yes - add Posted within (days) = 1 and run it on an Apify Schedule to get fresh matches for your description every day.

Is this legal? The data comes from publicly posted job listings on company career pages, accessed via the Hirebase API.