OUR RECRUITMENT TECHNOLOGY

Sophisticated Machine Learning for the Recruiting Industry

The industry’s first & only
AI-platform built to unleash

the full recruiting power of Google for Jobs

While our HR technology is sophisticated, our solution is simple. Jobiak enables employers and talent acquisition partners to easily publish and optimize job listings on Google for Jobs.

Our state-of-the-art Machine Learning (ML) eliminates the technology challenges that previously limited access to this incredible new recruiting channel, empowering clients to achieve extraordinary results that no other recruitment technology can deliver. 

key to unlocking the recruiting power of Google
lightning powered AI tech

Incredible Recruitment Technology.

Incredibly easy to implement.

Jobiak is the only recruitment technology solution with the power to fully automate and optimize listings on Google for Jobs, in as little as 48 hours.

Up To4xThe Applications
Top 20Ranking

AI-Powered SEO boosts every job into the top 20
rankings, dramatically increasing your job applicant
volume, quality and relevancy

THE MAKING OF OUR MACHINE LEARNING

Over 80,000 man-hours went into developing our patent-pending recruitment technology, which was built by exceptional engineers with deep expertise in the recruiting and Machine Learning industries. Our Artificial Intelligence (AI) model is constantly trained to generate high-performing keywords and make real-time SEO adjustments based on local market demand.

TRAINING DATASET

400,000 man-hours of data collection were invested to create our AI-model, which has scoured million of job descriptions to ensure a high degree of accuracy

3.5 MILLIONJob Listings
600,000Job Titles
58,000Competencies
(e.g., data analytics, UX design)

recruitment technology

machine learning
expertise

50 Years of Machine Learning Expertise

More than 20 specific machine-learning algorithms

recruitment technology

patent-pending
technology

More than 100 Engineers involved in product dev

Over 60 years of industry experience in recruiting and intellectual property (IP) development

relational
model

118 million occupational associations

600,000 nodes and 27 million edges between title and descriptions

127 million associations between titles and skills

THE MOST POWERFUL PREDICTIVE TECHNOLOGY
FOR JOB POST OPTIMIZATION

Jobiak’s AI-platform accounts for over 25 “signals” that factor into Google for Jobs
rankings and uses sophisticated modeling to implement the optimal code to
achieve top search results for your job posts

machine learning
GOOGLE FOR JOBS RANKING FACTORS

Key SEO Signals

(Company name in domain, keyword presence, SEO meta tags)

Job Personalization Signals

(High-ranking titles, title and job description associations)

Company Reviews Signals

(Number of reviews, ratings, similar jobs)

On-Page Signals

(Occupational category, company logo, salary estimates)

Real-Time, Market-Based Signals

(Most-searched queries by job-seekers, commonly used job-search keywords, frequency of re-posting)

Location Signals

(Location accuracy, nearby locations, population size, address and zip code)

THE ANATOMY OF AN OPTIMIZED JOB POST

Jobiak automatically optimizes your job posts for high ranking using machine-generated keywords, titles and descriptions, based on analysis of both real-time information and learnings from millions of monitored postings.

Our AI-platform executes over 25 specialized SEO techniques both on the front-end of the post that job-seekers see on Google for Jobs, and in the background, to optimize the underlying code.

FRONT-END OPTIMIZATIONS

Url
JOB TITLE
COMPANY LOGO
COMPANY NAME
LOCATION
DIRECT APPLY
OCCUPATIONAL CATEGORY
FREQUENT REPOSTING
SKILLS & SPECIALTIES
JOB DESCRIPTION
SALARY ESTIMATES
COMPANY REVIEWS

Back-END OPTIMIZATIONS

SEO META TAGS
ML GENERATED KEY WORDS
REAL-TIME UPDATES
NEARBY LOCATIONS

OUR MACHINE LEARNING ENGINE

Jobiak scans your jobs and identifies the 11 attributes that
Google requires for Google for Jobs posts

The recruitment technology used to process these 11 attributes:

SKIP
SKIP
Job Identifier
Identify distinct components of JOB IDENTIFIER (Ref Job, Job Id etc)

Job IDs are hard to recognize since a job page is usually littered with various types of IDs that resemble a job ID. Jobiak’s learning algorithms can accurately separate and extract the correct job ID from the rest.

Company
HTML Structure Analysis
Weighting Heuristics
NLP
Random Decision Forest
N-Gram Model
X-Paths

Hiring company name can appear anywhere on a job description page. Sometimes part of a large blob of text, sometimes as a image logo on the page or simply implied by the URL. The presence of other company names (like the hosting job board) or company name like entities make it even more difficult to accurately identify the hiring company.

Jobiak’s sophisticated natural language processing and modeling techniques are capable of automatically distinguishing the correct company name from others. This is aided by Jobiak’s proprietary visual/structural parsing technology as well as millions of carefully curated and labelled data.

Title
Patterns/Regular Expressions
Remove Non-relevant sections(similar jobs, more jobs etc)
HTML Structure Analysis
Text Mining (Tf-Idf)
Random Decision Forest
NLP
Weighting Heuristics
Lookup table
N-Gram Model
Identify distinct components of Job titles(Ref Job, Job Id etc)

Job titles are unstructured and can appear anywhere on a job description page often along with other entities like job location, requisition number etc. making it extremely difficult to automatically extract.

Jobiak’s sophisticated natural language processing and modeling techniques utilize 100s of visual, structural and semantic features to recognize and extract job titles with a high degree of accuracy from any unstructured web page. This is aided by Jobiak’s proprietary visual/structural parsing technology as well as millions of carefully curated and labelled data items.

Location
Patterns/Regular Expressions
Random Decision Forest
Weighting Heuristics
Identify Location Component(Cities, states, Regions, Countries)
XPaths
N-Gram Model

Locations are unstructured, can appear anywhere on the page, often incomplete and along with other entities like job title or in the middle of a large description making it difficult to extract .

Jobiak’s sophisticated natural language processing and modeling techniques are capable of automatically identifying job locations anywhere on the page with a high degree of accuracy as well as canonicalizing it based on contextual information. This is aided by Jobiak’s proprietary visual/structural parsing technology as well as millions of carefully curated and labelled data.

Description
Unsupervised Topic Model(Latent Dirichlet Allocation)/span>
Sentence classification Model(Random Decision Forest)
Decision Hints
Job Description Detector(density based algorithm)

Accurately identifying description is a hard task. Descriptions are made up of large portions of text, often with multiple sections. Accurately identifying text that is part of a job description and identifying the beginning and end of description sections becomes hard, even for human reviewers.

Jobiak employs sophisticated machine learning techniques to identify various sections and topics that are part of the description and accurately classify sections that are part of the description. The technology also uses various algorithms to determine the boundaries of the description so as to accurately extract a description in it’s entirety, no more or no less than what is actually the description.

Salary
Weighting Heuristics
N-Gram Model
Xpaths
Identify Salary Components(periodic, range, simple, descriptive etc)

Jobiak’s algorithms can accurately identify salaries in job descriptions usually written in various formats (ranges), currencies and units (hourly, annually).

Job Type
Weighting Heuristics
Identify distinct components of Job type(Full Time, Contractor, Part time etc)
NLP
N-Gram Model
Xpaths
Deep Neural Network

Various job types associated with a job are identified whether it is explicitly present in the job page or inferred through context.

Posting Date
Identify distinct components of posting date(Posted Date, Posted since etc)
N-Gram Model
Xpaths

Jobiak’s algorithms can accurately detect and distinguish between various kinds of dates like posted dates, validity dates, age etc

Valid Through
Identify distinct components of valid through date(Closes on, Valid through etc)
N-Gram Model
Xpaths
Common
SUPERVISED MODEL FOR CERTAIN TAGS
N-Gram Model
Xpaths
Optimization
Identify Location, JOB ID & SKILL ComponentS
Supervised model for certain tags
Power mean & graph embeddings
10 convolutional neural networks

Jobiak’s optimization technology is built using sophisticated machine learning algorithms trained using millions of job postings and their online performance over a long period of time. Jobiak has built knowledge structures such as association graphs of titles, skills, descriptions using sophisticated text processing techniques. Convolutional models trained on this data accurately recommend proven job optimizations required to improve online visibility for job listings.