Production System

What's behind FitToHire

A purpose-built extraction and matching engine — trained on real hiring data, not generic language models.

The scale

Real numbers from the production system.

🧠
0
Normalized Skills
💬
0
Contextual Phrases
0
Trigger Phrases
🗂️
0
Skill Domains
🔗
0
Training Pairs

26 domains

Every skill lives in a domain with its own vocabulary, relationships, and context rules.

Healthcare
18,153
skills
Business
16,681
skills
Technology
14,224
skills
Engineering
12,984
skills
Construction
11,553
skills
Legal
11,002
skills
Trades
9,773
skills
Creative
8,821
skills
Education
7,438
skills
Transportation
7,012
skills
Government
6,913
skills
Enterprise Systems
6,538
skills
Scientific
6,381
skills
Manufacturing
6,024
skills
Retail
5,669
skills
Energy
5,560
skills
Insurance
5,395
skills
Nonprofit
4,628
skills
Agriculture
4,024
skills
Media
3,758
skills
Sports
3,752
skills
Real Estate
3,656
skills
Consulting
3,075
skills
Soft Skills
2,917
skills
Mining
2,875
skills
Telecommunications
2,732
skills

191,538 total skills across all domains

The language layer

2.2 million phrases mapped to normalized skills. Watch how a resume phrase becomes a match.

Technology
“managed AWS infrastructure across 3 regions”
AWS Infrastructure
Engineering
“built CI/CD pipelines using Jenkins and GitHub Actions”
CI/CD Pipeline Design
Soft Skills
“led cross-functional teams of 12 engineers”
Team Leadership
Healthcare
“implemented HIPAA compliance controls”
HIPAA Compliance
Technology
“designed RESTful APIs serving 10M requests/day”
REST API Design
Technology
“optimized PostgreSQL queries reducing p95 by 40%”
SQL Optimization

825,000 trigger phrases in Tier A alone — covering every way people describe skills

The comparison

Every skill classified. Every gap identified.

Job Requirement
Your Resume
Status
Kubernetes
Kubernetes
matched
Docker
Docker, Podman
matched
Terraform
CloudFormation
partial
Go
missing
AWS
AWS, GCP
matched
PostgreSQL
MySQL, Redis
partial

How it works

Six stages from raw text to an explainable score.

Three-Mode Extraction

Three independent extractors — lexicon lookup, neural span detection, and full-text scanning — process every document. Results are merged and deduplicated.

Skill Normalization

191K skills across 26 domains with concept-key dedup. "AWS infrastructure management" and "managed AWS infra" resolve to the same canonical skill.

Cross-Encoder Disambiguation

When a phrase maps to multiple skills, a fine-tuned cross-encoder trained on 2M real job description pairs picks the right one from context.

Evidence-Based Scoring

Every matched skill links back to the exact phrase in your resume. No black boxes — every score point is explainable.

Requirement Weighting

Must-haves, preferred, and nice-to-haves are classified separately. A missing must-have weighs more than a missing nice-to-have.

Quality Gate

A diagnostics layer checks extraction quality before scoring. Low confidence gets flagged, not guessed.

See it work on your resume

No signup required. Results in 30 seconds.

Try FitToHire