Zorlya is on Product Hunt today. See the launch and tell us what you think.
See the launch
How Zorlya scores and matches jobs, where the jobs come from, and what the dates and salaries on a posting mean.
Plain explanations of the data behind every score, with what it cannot tell you.
The posts to read first in this hub.
Your resume is parsed into fields, split into passages and turned into embeddings, all stored in Zorlya's own database. Passages are sent to a model only to score, explain or draft, and the default model runs on Cloudflare Workers AI. You can delete files one at a time or the whole account in one step.
Zorlya reads public job boards and applicant tracking systems, the software employers post their own openings on. Every source is one that permits automated reading. LinkedIn, Indeed, Glassdoor and more than 20 other sites were checked and left out, each for a recorded reason.
Every job gets a score from 0 to 100, built from four parts, and a fifth when the posting states a seniority level. Resume fit, skills match, salary fit and location fit are scored separately, weighted, and combined, and a part with nothing to measure is left out instead of counted as average.
Newest first.
Some employers never post on a job board. They hire through their own website, through networks, or through a system that no aggregator reads. If an employer you want is missing, go to its own careers page, look for sector sources, and ask for it to be added.
AI job search is software that reads your resume and a pool of postings, then ranks the postings by how closely they match. It finds roles you would not have searched by title, and it fails on thin postings, stale data and rankings it cannot explain. Six questions tell you whether a tool deserves your time.
To find jobs based on your resume, a matching tool reads your resume into a profile, compares it with posted jobs and ranks them. Judge the results by checking the reasons and the misses, not only the top of the list.
A job index is a stored copy of postings gathered from many sources. On 24 October 2026 about one in five of the live jobs in Zorlya's index had no country recorded, and most known companies had no live job. These figures change daily, and none of them tells you how many openings are real.
Your resume is parsed into fields, split into passages and turned into embeddings, all stored in Zorlya's own database. Passages are sent to a model only to score, explain or draft, and the default model runs on Cloudflare Workers AI. You can delete files one at a time or the whole account in one step.
Zorlya reads public job boards and applicant tracking systems, the software employers post their own openings on. Every source is one that permits automated reading. LinkedIn, Indeed, Glassdoor and more than 20 other sites were checked and left out, each for a recorded reason.
Find the same job on the employer's own website, check that the contact address uses the employer's real domain, and never pay or send ID documents before a confirmed offer. Five checks take about 15 minutes and remove much of the risk.
A posting can carry three different dates. Posted is when the ad appeared, the deadline is the last day the employer says it will take applications, and closed is when it stops taking them. Only the deadline is a promise, and even that depends on the time zone and the employer.
The date on a card is whatever the source reported, and sources mean different things by it, so treat it as a hint. Some give the day an ad was first published, some the day it was last edited, and a few give nothing, in which case Zorlya's date window for matching uses the day it first saw the posting.
Zorlya stores a salary as a number only when the source gives a yearly figure. Hourly and monthly pay stays as the text the source wrote. A posting with no salary is never scored as zero. How it counts depends on whether you set a salary floor.
Zorlya calls a language model to write for you and to judge fit, and uses plain code for arithmetic, matching and lookups. A project to replace more model calls with rules is built but still running in shadow mode, which means nothing has been switched over yet.
Job matching compares what you have done with what a posting asks for and turns the comparison into a ranking or a score. Two tools disagree because they hold different jobs, read your resume differently, weight the parts differently and treat missing facts differently.
Showing 1 to 12 of 15 posts
