HrFlow background
The HR-Native Recommender System for Profiles & Jobs (Ranker & RecSys)

Scoring API

The Scoring API serves a two-sided, large-scale recommendation engine (RecSys) for ranking Jobs for people and people for Jobs across roles (blue-collar and white-collar) and seniority levels (junior to senior). Powered by Hiring Superintelligence, it is pre-trained on 1.2B hiring decisions to deliver outcome-based probability scores with built-in fairness mitigation and EU AI Act explainability.

Read the Docs
~83% accuracy
10M/s index throughput
1.2B trainset
GDPR & EU AI Act
99.99% uptime
output.json
{
  "parsing": {
    "model": "hrflow-file-v2.1",
    "confidence": 0.92,
  },
  "profile": {
    "name": "John Smith",
    "title": "Data Scientist",
    "skills": ["ML", "Python"]
  }
}

Trusted by Customers, Partners & the AI Ecosystem

ManpowerLogo
CritLogo
EuropeanUnionLogo
SanofiLogo
EnhanceCVLogo
TeamtailorLogo
API REQUEST

Hybrid Ranking & Search

Query Profiles or Jobs and get ranked hits (JSON) with probability match scores (Softmax: 1-score, score) plus pagination metadata (total, page, limit, …). Scores are computed via hierarchical predictions over full profile + job context, so ranking reflects real hiring fit, not keyword overlap.

Select Scoring Type

Query profiles → returns ranked Profile hits (JSON) + Softmax Predictions (1-score, score) + pagination metadata (total, page, limit, …).

Explore

API GuideAPI EndpointTry Live Demo

Top Query Fields

Anchor Job

key or reference, and board

Scoring Algorithm

Recruiter-side: Corporate, Staffing Agency, Recruiting firm, Consulting firm

Memory Context

real-time learning from user or org actions.

Memory Context Warmup

preload similar historical user/org signals.

Search Params

(Searching API): keywords, Geo, Ranges, Facets, Taxonomies, Raw filters

Score Threshold

minimum hit score

Pagination & Sorting

index (source/board), page, limit, sort_by, order_by

response.json
 1{
 2  "code": 200,
 3  "message": "Scoring completed successfully.",
 4  "meta": {
 5    "page": 1,
 6    "limit": 10,
 7    "total": 847
 8  },
 9  "data": [
10    {
11      "profile": {
12        "key": "abc123",
13        "info": {
14          "first_name": "Sarah",
15          "last_name": "Chen",
16          "location": "San Francisco, CA"
17        },
18        "skills": ["Python", "ML", "NLP"],
19        "experiences_duration": 7.2
20      },
21      "predictions": [0.06, 0.94]
22    },
23    {
24      "profile": {
25        "key": "def456",
26        "info": {
27          "first_name": "James",
28          "last_name": "Park",
29          "location": "New York, NY"
30        },
31        "skills": ["Data Science", "PyTorch"],
32        "experiences_duration": 5.1
33      },
34      "predictions": [0.13, 0.87]
35    }
36  ]
37}
CUSTOMER STORIES

Don't take our word for it!

Trusted by fast-growing HR Tech and Global Enterprise

“

Outcome-based hiring, finally

vs. Google Vertex
Before HrFlow.ai

Vertex isn't HR-native, so the recommendations were generic and not hiring-outcome based. We ended up doing heavy post-processing, but we still couldn't cover every case.

After HrFlow.ai

HrFlow.ai gave us a production-ready, outcome-based Scoring API with built-in monitoring and fairness controls.

“

No more taxonomy maintenance

vs. Textkernel
Before HrFlow.ai

Textkernel scoring was mostly keyword and taxonomy overlap. It required heavy taxonomy maintenance and still struggled with complex roles and frontline hiring.

After HrFlow.ai

HrFlow.ai replaced that with production-ready, zero-config probability scoring pre-trained for the hard cases.

“

No more slow queries at scale

vs. OpenAI LLM
Before HrFlow.ai

We manage ~1M profiles, so running an LLM over the full database per request wasn’t viable—latency would be measured in days, not seconds. We also saw unstable rankings, prompt-injection risks, and ChatGPT-written CVs being incorrectly favored.

After HrFlow.ai

HrFlow.ai replaced that with deterministic, HR-native scoring that’s fast, robust, and ships with built-in compliance features.

“

Outcome-based hiring, finally

vs. Google Vertex
Before HrFlow.ai

Vertex isn't HR-native, so the recommendations were generic and not hiring-outcome based. We ended up doing heavy post-processing, but we still couldn't cover every case.

After HrFlow.ai

HrFlow.ai gave us a production-ready, outcome-based Scoring API with built-in monitoring and fairness controls.

“

No more taxonomy maintenance

vs. Textkernel
Before HrFlow.ai

Textkernel scoring was mostly keyword and taxonomy overlap. It required heavy taxonomy maintenance and still struggled with complex roles and frontline hiring.

After HrFlow.ai

HrFlow.ai replaced that with production-ready, zero-config probability scoring pre-trained for the hard cases.

“

No more slow queries at scale

vs. OpenAI LLM
Before HrFlow.ai

We manage ~1M profiles, so running an LLM over the full database per request wasn’t viable—latency would be measured in days, not seconds. We also saw unstable rankings, prompt-injection risks, and ChatGPT-written CVs being incorrectly favored.

After HrFlow.ai

HrFlow.ai replaced that with deterministic, HR-native scoring that’s fast, robust, and ships with built-in compliance features.

“

Outcome-based hiring, finally

vs. Google Vertex
Before HrFlow.ai

Vertex isn't HR-native, so the recommendations were generic and not hiring-outcome based. We ended up doing heavy post-processing, but we still couldn't cover every case.

After HrFlow.ai

HrFlow.ai gave us a production-ready, outcome-based Scoring API with built-in monitoring and fairness controls.

“

No more taxonomy maintenance

vs. Textkernel
Before HrFlow.ai

Textkernel scoring was mostly keyword and taxonomy overlap. It required heavy taxonomy maintenance and still struggled with complex roles and frontline hiring.

After HrFlow.ai

HrFlow.ai replaced that with production-ready, zero-config probability scoring pre-trained for the hard cases.

“

No more slow queries at scale

vs. OpenAI LLM
Before HrFlow.ai

We manage ~1M profiles, so running an LLM over the full database per request wasn’t viable—latency would be measured in days, not seconds. We also saw unstable rankings, prompt-injection risks, and ChatGPT-written CVs being incorrectly favored.

After HrFlow.ai

HrFlow.ai replaced that with deterministic, HR-native scoring that’s fast, robust, and ships with built-in compliance features.

“

Outcome-based hiring, finally

vs. Google Vertex
Before HrFlow.ai

Vertex isn't HR-native, so the recommendations were generic and not hiring-outcome based. We ended up doing heavy post-processing, but we still couldn't cover every case.

After HrFlow.ai

HrFlow.ai gave us a production-ready, outcome-based Scoring API with built-in monitoring and fairness controls.

“

No more taxonomy maintenance

vs. Textkernel
Before HrFlow.ai

Textkernel scoring was mostly keyword and taxonomy overlap. It required heavy taxonomy maintenance and still struggled with complex roles and frontline hiring.

After HrFlow.ai

HrFlow.ai replaced that with production-ready, zero-config probability scoring pre-trained for the hard cases.

“

No more slow queries at scale

vs. OpenAI LLM
Before HrFlow.ai

We manage ~1M profiles, so running an LLM over the full database per request wasn’t viable—latency would be measured in days, not seconds. We also saw unstable rankings, prompt-injection risks, and ChatGPT-written CVs being incorrectly favored.

After HrFlow.ai

HrFlow.ai replaced that with deterministic, HR-native scoring that’s fast, robust, and ships with built-in compliance features.

“

From cosine similarity to hiring likelihood

vs. Cohere/Pinecone
Before HrFlow.ai

Cohere vectors gave us cosine similarity, not hiring relevance. Two candidates may be semantically similar, but only one has the right prerequisites. We kept compensating with patchworks of rules and taxonomies.

After HrFlow.ai

HrFlow.ai replaced that with HR-native, pre-trained rankers optimized for hiring outcomes that stay accurate as recruiter behavior and market conditions evolve.

“

No more DevOps burden

vs. ElasticSearch
Before HrFlow.ai

Elasticsearch gave us keyword overlap, not hiring relevance. We had to build and maintain taxonomies, tune analyzers, and operate the search stack—then still patch edge cases for multilingual data and frontline hiring.

After HrFlow.ai

HrFlow.ai replaced that with HR-native probability scoring plus hybrid filters, without the taxonomy and search-engine overhead.

“

Beyond keywords and taxonomies

vs. AdeptID
Before HrFlow.ai

AdeptID worked for basic scoring, but we needed a broader end-to-end stack: multilingual ranking, deterministic scoring, online/offline fine-tuning, and EU AI Act-aligned monitoring.

After HrFlow.ai

HrFlow.ai covered everything in a single system.

“

From cosine similarity to hiring likelihood

vs. Cohere/Pinecone
Before HrFlow.ai

Cohere vectors gave us cosine similarity, not hiring relevance. Two candidates may be semantically similar, but only one has the right prerequisites. We kept compensating with patchworks of rules and taxonomies.

After HrFlow.ai

HrFlow.ai replaced that with HR-native, pre-trained rankers optimized for hiring outcomes that stay accurate as recruiter behavior and market conditions evolve.

“

No more DevOps burden

vs. ElasticSearch
Before HrFlow.ai

Elasticsearch gave us keyword overlap, not hiring relevance. We had to build and maintain taxonomies, tune analyzers, and operate the search stack—then still patch edge cases for multilingual data and frontline hiring.

After HrFlow.ai

HrFlow.ai replaced that with HR-native probability scoring plus hybrid filters, without the taxonomy and search-engine overhead.

“

Beyond keywords and taxonomies

vs. AdeptID
Before HrFlow.ai

AdeptID worked for basic scoring, but we needed a broader end-to-end stack: multilingual ranking, deterministic scoring, online/offline fine-tuning, and EU AI Act-aligned monitoring.

After HrFlow.ai

HrFlow.ai covered everything in a single system.

“

From cosine similarity to hiring likelihood

vs. Cohere/Pinecone
Before HrFlow.ai

Cohere vectors gave us cosine similarity, not hiring relevance. Two candidates may be semantically similar, but only one has the right prerequisites. We kept compensating with patchworks of rules and taxonomies.

After HrFlow.ai

HrFlow.ai replaced that with HR-native, pre-trained rankers optimized for hiring outcomes that stay accurate as recruiter behavior and market conditions evolve.

“

No more DevOps burden

vs. ElasticSearch
Before HrFlow.ai

Elasticsearch gave us keyword overlap, not hiring relevance. We had to build and maintain taxonomies, tune analyzers, and operate the search stack—then still patch edge cases for multilingual data and frontline hiring.

After HrFlow.ai

HrFlow.ai replaced that with HR-native probability scoring plus hybrid filters, without the taxonomy and search-engine overhead.

“

Beyond keywords and taxonomies

vs. AdeptID
Before HrFlow.ai

AdeptID worked for basic scoring, but we needed a broader end-to-end stack: multilingual ranking, deterministic scoring, online/offline fine-tuning, and EU AI Act-aligned monitoring.

After HrFlow.ai

HrFlow.ai covered everything in a single system.

“

From cosine similarity to hiring likelihood

vs. Cohere/Pinecone
Before HrFlow.ai

Cohere vectors gave us cosine similarity, not hiring relevance. Two candidates may be semantically similar, but only one has the right prerequisites. We kept compensating with patchworks of rules and taxonomies.

After HrFlow.ai

HrFlow.ai replaced that with HR-native, pre-trained rankers optimized for hiring outcomes that stay accurate as recruiter behavior and market conditions evolve.

“

No more DevOps burden

vs. ElasticSearch
Before HrFlow.ai

Elasticsearch gave us keyword overlap, not hiring relevance. We had to build and maintain taxonomies, tune analyzers, and operate the search stack—then still patch edge cases for multilingual data and frontline hiring.

After HrFlow.ai

HrFlow.ai replaced that with HR-native probability scoring plus hybrid filters, without the taxonomy and search-engine overhead.

“

Beyond keywords and taxonomies

vs. AdeptID
Before HrFlow.ai

AdeptID worked for basic scoring, but we needed a broader end-to-end stack: multilingual ranking, deterministic scoring, online/offline fine-tuning, and EU AI Act-aligned monitoring.

After HrFlow.ai

HrFlow.ai covered everything in a single system.

🔗 INTEGRATIONS

Works with the tools you use

Integrate thousands of tools and hundreds of HR systems with a flip of a switch.

Integration 0
Integration 1
Integration 2
Integration 3
Integration 4
Integration 5
Integration 6
Integration 7
Integration 8
Integration 9
Integration 10
Integration 11
Integration 0
Integration 1
Integration 2
Integration 3
Integration 4
Integration 5
Integration 6
Integration 7
Integration 8
Integration 9
Integration 10
Integration 11
Integration 0
Integration 1
Integration 2
Integration 3
Integration 4
Integration 5
Integration 6
Integration 7
Integration 8
Integration 9
Integration 10
Integration 11
Integration 0
Integration 1
Integration 2
Integration 3
Integration 4
Integration 5
Integration 6
Integration 7
Integration 8
Integration 9
Integration 10
Integration 11
HrFlow.ai Data Studio

HrFlow.ai Data Studio

HR-native ETL with 200+ connectors plus Webhooks to ingest, normalize, and sync jobs & profiles across your stack, reliable pipelines with unified schemas.

Zapier ETL

Zapier ETL

No-code automation platform with 8,000+ app integrations to move data between tools using triggers + actions.

Make.com ETL

Make.com ETL

Visual automation platform to extract/transform/route data across 3,000+ apps (plus HTTP modules for any API).

Microsoft Flow ETL

Microsoft Flow ETL

Microsoft Power Automate, workflow automation with 1,000+ API connectors (and support for custom connectors).

Workato ETL

Workato ETL

Enterprise iPaaS/automation platform with 1,200+ pre-built connectors for orchestrating integrations and data workflows at scale.

Salesforce Flow Automation

Salesforce Flow Automation

Salesforce's low-code workflow automation tool; extended via AppExchange with 7,000+ apps to add integrations and capabilities.

🚀 KEY FEATURES

End-to-End Scoring Stack: Large-Scale Inference, Finetuning, and Responsible AI

HrFlow.ai Scoring is a large-scale two-sided recommender system for People ↔ Jobs scoring that combines hierarchical deep encoders (full profile + job content), deterministic probability scoring, and a two-stage pipeline (high-throughput retrieval/ANN index + optional Grading API reranking) with multilingual/cross-lingual representations. It supports hybrid search filters, explainability, feature fusion (tags, metadata, tabular signals), personalization and intent modeling (memory context, session signals), and online/offline fine-tuning driven by tracked recruiter/candidate events, with fairness-regularized training, data calibration pipelines, and built-in monitoring for performance and bias, aligned with EU AI Act and International Ethical AI requirements.

Tutorial Video3:45

🔒 ENTERPRISE-READY

Trust & Security

Built for sensitive HR data, secure by default, enterprise-ready.

01

Encryption

TLS in transit + encryption at rest to protect documents and extracted data.

02

Retention control

Minimal storage by default, with configurable retention policies to match your compliance needs.

03

AI-Act / GDPR / DPA ready

AI-Act & GDPR-ready processing and Data Processing Agreement (DPA) are available on request.

04

Location / Region

Data processing and storage can be aligned with your required region (e.g., EU or US) depending on your deployment.

Visit Trust Center→
📊 FEATURE COMPARISON

HrFlow.ai Scoring is the Most accurate and complete ranking stack for People & Jobs HR Data

Feature
HrFlow.ai Scoring
HrFlow.ai Scoring
Google Vertex
Google Vertex
OpenAI LLM
OpenAI LLM
Textkernel
Textkernel
Cohere Vectors
Cohere Vectors
Pinecone DB Vectors
Pinecone DB Vectors
AdeptID
AdeptID
ElasticSearch
ElasticSearch
Deployment & Trust
Headquarters
🇫🇷 France
🇺🇸 USA
🇺🇸 USA
🇳🇱 Netherlands
🇺🇸 USA
🇺🇸 USA
🇺🇸 USA
🇺🇸 USA
🇺🇸 USA & 🇪🇺 EU Servers
Built-in
Built-in
Built-in
Built-in
Built-in
Built-in
USA only
Built-in
GDPR / AI-Act
By design
By design
By design
By design
By design
By design
Partial
By design
HR Compliance (Safety & Guardrails)
Built-in
None
None
Partial
None
None
Partial
None
HR-Focused
Zero-config (HR)
On-premise / Private Cloud
Available
Available
Enterprise
Available
Enterprise
Enterprise
Enterprise
Available
SLA & Uptime Guarantee
99.9%
99.9%
99.9%
Partial
99.9%
99.9%
Partial
99.9%
API-first Design
Dedicated Support
Built-in
Enterprise
Enterprise
Enterprise
Enterprise
Enterprise
Built-in
Enterprise
No Data Training on Customer Data
Guaranteed
Opt-out
Opt-out
Guaranteed
Opt-out
Guaranteed
Guaranteed
Guaranteed
ISO 27001 / SOC2
Certified
Certified
Certified
Certified
Certified
Certified
In progress
Certified
Bias & Fairness Audit
Built-in
None
None
Partial
None
None
Partial
None
Explainability / Score Rationale
Built-in
Partial
Partial
Partial
None
None
Partial
None
Audit Logs & Traceability
Built-in
Built-in
Built-in
Partial
Partial
Partial
Partial
Built-in
Core Technology
Scoring Approach
HR-native ML + Embeddings
General ML / LLM
Prompt-based LLM
Rule-based + ML
Vector similarity
Vector similarity
HR-specific ML
BM25 + Vector
Resume ↔ Job Matching
Job ↔ Job Similarity
Resume ↔ Resume Similarity
Semantic Scoring
HR-native
General
General
Partial
General
General
HR-native
General
Structured Field Scoring
Skills, exp, edu, location
Partial
Partial
Skills, exp, edu
None
None
Skills, exp
Partial
Weighted Criteria Scoring
Custom Scoring Profiles
Built-in
Via fine-tuning
Via prompts
Partial
None
None
Partial
None
Multilingual Scoring
43+ languages
100+ languages
100+ languages
29 languages
100+ languages
100+ languages
EN/ES/FR
100+ languages
Real-time Scoring (<500ms)
Built-in
Partial
Too slow
Built-in
Built-in
Built-in
Partial
Built-in
Batch Scoring at Scale
Score Normalization (0–1)
Diversity / DEI Scoring Mode
Built-in
None
None
None
None
None
Partial
None
Location / Geo Scoring
Built-in
None
None
Partial
None
None
Partial
Partial
Salary / Compensation Scoring
Built-in
None
None
None
None
None
Partial
None
Model Accuracy (HR Benchmark)
Top-tier HR
General
General
High HR
General
General
High HR
General
Continuous Model Updates
Quarterly
Frequent
Frequent
Annual
Frequent
Frequent
Partial
Frequent
Human-in-the-loop Feedback
Built-in
Via fine-tuning
Via fine-tuning
None
None
None
Partial
None
No Hallucination Risk
Guaranteed
Partial
LLM risk
Guaranteed
Guaranteed
Guaranteed
Guaranteed
Guaranteed
Cost per 1K Scorings
Low (flat API)
Medium
High (token-based)
Medium
Medium
Medium
Medium
Low
HR Stack integrations (add-ons)
Resume, CV, Job parsers
Built-in (Parsing API)
Partial
HR Tagging / Skills Taxonomy
Built-in (Tagging API)
Partial
Partial
Search Engine Add-on
Built-in (Searching API)
Core product
Embedding / Vector Store
Built-in (Embedding API)
Vertex Embeddings
OpenAI Embeddings
Core product
Core product
Partial
Recommender System Add-on
Built-in (Scoring API)
Partial
Jobboards / ATS / HCM / HRIS connectors
200+ HR connectors (Data Studio)
Some ATS
Some ATS
Candidate & Recruiter UI
Widgets (App Studio)
Analytics & Reporting Dashboard
Built-in
Partial
None
Partial
None
None
Partial
Partial
❓ COMMON QUESTIONS

Frequently Asked Questions

Everything you need to know about the Scoring API

🧩 COMPLETE API SUITE

Go beyond the Scoring API

Our APIs are designed to complement each other and unlock your data's full potential

Full Extraction API Suite

Transform HR documents into structured, enriched Talent & Workforce Data — powering every layer of Hiring Intelligence.

API Overview
94%82%71%58%

Ranking API Suite

Unlock Hiring Superintelligence at scale — with transparent, fair, and explainable ranking across every Talent signal.

API Overview

GET STARTED

Ready to transform your HR data?

Start parsing resumes and job postings in minutes with our powerful API.

Start for free→Talk to sales

HrFlow.ai is an API-first company and the leading AI-powered HR data automation platform.

The company helps +1000 customers (HR software vendors, Staffing agencies, large employers, and headhunting firms) to thrive in a high-volume and high-frequency labor market.

The platform provides a complete and fully integrated suite of HR data processing products based on the analysis of hundreds of millions of career paths worldwide -- such as Parsing API, Tagging API, Embedding API, Searching API, Scoring API, and Upskilling API. It also offers a catalog of +200 connectors to build custom scenarios that can automate any business logic.

GDPR Compliant badgeCapterra 4.8 rating badge

SOLUTIONS

PRODUCT

RESOURCES

COMPANY