Recruit Assist AI app for HR Mind

About HR Mind

HR Mind is a global resourcing company founded in 2010 that offers end-to-end recruitment and HR solutions to organisations in domestic and international markets. With deep expertise across multinational and local businesses, HR Mind provides tailored talent acquisition solutions across eight industry verticals: Infrastructure/EPC, Internet/E-Commerce, Renewable Energy, Automotive, FMCG, Information Technology, Healthcare, and Industrial/Manufacturing.

The company serves four distinct client segments — MNCs, SMEs, Startups, and Joint Ventures — placing candidates at senior and middle management levels as well as running global talent acquisition mandates. Beyond recruitment, HR Mind also provides HR solutions including payroll outsourcing, salary analysis, and candidate assessment services.

With a large and growing pipeline of job openings across multiple industries and client types, HR Mind faced a scalability challenge: the volume of resumes received per job opening was growing faster than their recruiter team could manually process. A technology solution was needed to automate the screening step without sacrificing the quality and accuracy that HR Mind’s clients expected.

The Problem

Recruitment at scale is fundamentally a data matching problem — but one that had been solved manually for decades. HR Mind identified several specific pain points driving the need for an AI solution:

High volume, low signal — hundreds of resumes received per job opening, with the majority not matching the role requirements. Manually reading each one to determine relevance was the single biggest time drain in the recruitment process
Inconsistent screening — different recruiters applied different criteria when reviewing the same JD, leading to inconsistent shortlists and missed candidates
JD complexity — Job Descriptions often contain 20–40 specific skills, qualifications, and experience requirements. Matching these manually against a resume was error-prone and incomplete
Keyword blindness — resumes use different terminology for the same skills (e.g. ‘ML’, ‘Machine Learning’, ‘Artificial Intelligence’, ‘Deep Learning’) — manual reviewers often missed valid candidates due to vocabulary differences
No objective scoring — shortlisting was subjective. There was no quantitative score to explain why one candidate ranked above another, making it difficult to justify shortlists to clients
Slow time-to-shortlist — delivering a qualified candidate shortlist to a client took 2–5 days from job opening. In competitive talent markets, this delay cost placements
Inability to re-use candidate pool — past resumes in the database were not being systematically re-matched against new job openings — a significant lost opportunity

Scope & Feature List

Module 1 — Job Description (JD) Parsing & Keyword Extraction

The platform begins every recruitment workflow by intelligently parsing the Job Description to extract the structured requirements the AI will match resumes against:

NLP-powered JD parsing — the system reads the full Job Description and extracts structured data: required skills, preferred skills, qualifications, years of experience, seniority level, industry context, and location requirements
Keyword taxonomy — extracted keywords are classified into categories: hard skills (technical), soft skills (behavioural), certifications, tools/technologies, domain knowledge, and education requirements
Semantic keyword expansion — the AI expands the keyword list with synonyms and related terms (e.g. ‘Project Manager’ → also matches ‘Programme Manager’, ‘PM’, ‘Delivery Lead’) — preventing missed matches due to vocabulary differences
Weighted keyword scoring — keywords are automatically weighted by importance based on their position and frequency in the JD (e.g. ‘Required’ skills weighted higher than ‘Preferred’)
JD templates — HR Mind recruiters can save and reuse JD keyword profiles for recurring role types, speeding up future searches
Manual keyword adjustment — recruiters can add, remove, or re-weight keywords before running the matching engine — giving full control over the AI’s scoring criteria

Module 2 — Resume Ingestion & Classification

Resumes are ingested in bulk from multiple sources and automatically classified before matching begins:

Multi-format ingestion — resumes accepted in PDF, Word (.doc/.docx), and plain text formats — uploaded in bulk or individually
AWS S3 storage — all resumes stored securely in S3 with unique identifiers, version control, and encrypted storage at rest
Automated text extraction — AWS Textract used for PDF parsing (including scanned documents), ensuring structured text is available for NLP processing regardless of resume format
ML Resume Classification — each resume is automatically classified into a role category (e.g. Engineering, Sales, Finance, Technology, Operations, Healthcare) using a trained classification model — enabling filtering before matching
Structured data extraction — the AI parses each resume to extract: candidate name, contact details, current and previous job titles, companies, employment tenure, education level and institution, skills and technologies, certifications, and total years of experience
Duplicate detection — the system identifies duplicate or near-duplicate resumes (same candidate submitted multiple times or with minor edits) and flags them for recruiter review
Candidate database enrichment — parsed resume data is stored in DynamoDB against the candidate profile, building a searchable, structured talent pool over time

Module 3 — JD-to-Resume Keyword Matching Engine

The core intelligence of the platform — matching each resume against the parsed JD using multi-layer keyword and semantic analysis:

Exact keyword matching — each resume is scored for exact matches against the extracted JD keyword list (e.g. ‘Python’, ‘AWS’, ‘PMP certification’)
Semantic similarity matching — NLP embeddings identify candidates whose resumes are semantically similar to the JD even without exact keyword matches — reducing false negatives from vocabulary differences
Weighted match scoring — the overall match score is calculated as a weighted sum across keyword categories: hard skills carry the highest weight, followed by experience requirements, then education, then soft skills and location
Skills gap analysis — for each resume, the platform identifies which JD keywords are matched (green), partially matched (amber), and missing (red) — giving the recruiter an instant gap view
Experience relevance scoring — the AI assesses not just whether the candidate has a skill, but how recently and for how long they have used it — recent and sustained experience scores higher
Industry context matching — candidates from the same or closely related industries are scored higher for roles where domain knowledge matters
Multi-JD matching — a single resume pool can be simultaneously matched against multiple open job descriptions — surfacing the best fit role for each candidate in the database

Module 4 — AI Candidate Ranking & Shortlist Generation

The ranking engine takes match scores and produces a prioritised, explainable shortlist for the recruiter:

Composite ranking score — each candidate receives a final score (0–100) combining: JD keyword match score, experience relevance, education fit, industry match, and completeness of resume data
Ranked shortlist — candidates are listed in ranked order from highest to lowest match score — recruiter sees the best fits at the top immediately
Score breakdown per candidate — each candidate’s ranking is accompanied by a transparent breakdown: which keywords they matched, which they missed, their experience alignment, and their overall suitability percentage
Configurable shortlist size — recruiters can set the target shortlist size (e.g. top 10, top 20) — the system automatically surfaces the right number
Threshold filtering — recruiters can set a minimum match score threshold — only candidates above the threshold appear in the shortlist, filtering out weak matches automatically
Bias mitigation — ranking is based entirely on skills, experience, and JD alignment — personal information that could introduce bias (gender, age, ethnicity) is not factored into the scoring
Re-ranking on keyword edit — if the recruiter adjusts JD keywords or weights after an initial run, the ranking updates in real time without needing to re-process all resumes
Export to ATS — ranked shortlists exportable as CSV or integrated directly into HR Mind’s applicant tracking workflow for client presentation

Module 5 — Job Seeker Profile Scoring & Market Positioning

Beyond matching for a specific JD, the platform also scores each job seeker’s profile against the broader market — giving HR Mind and job seekers actionable intelligence:

Overall profile strength score — each job seeker receives an overall profile completeness and strength score based on: resume quality, skill breadth, experience depth, education, and keyword density
Market demand alignment — the system compares the candidate’s skill set against current JD demand signals across HR Mind’s active job openings — identifying which roles they are most competitive for
Skill gap recommendations — the platform identifies which skills or certifications, if added, would most improve the candidate’s match scores across active roles
Seniority level calibration — the AI assesses the candidate’s appropriate seniority band (Junior, Mid, Senior, Director) based on years of experience, role progression, and company tier — ensuring they are matched to appropriately levelled roles
Keyword optimisation feedback — candidates can receive feedback on which keywords are missing from their resume that appear frequently in their target role JDs — helping them improve their own resume for better matching
Historical match tracking — as new JDs are posted, the system automatically re-evaluates all stored candidate profiles and notifies recruiters when a previously low-scoring candidate is now a strong match for a new opening

Module 6 — Recruiter Intelligence Dashboard

A centralised interface giving HR Mind recruiters full visibility of the pipeline, AI results, and candidate insights:

Live pipeline view — all active job openings displayed with application counts, shortlist progress, and time-to-shortlist metrics
Candidate comparison view — side-by-side comparison of top-ranked candidates for a single JD — skills match, experience, score breakdown all visible simultaneously
Search and filter — recruiter can search the entire candidate database by keyword, classification, experience range, location, or score — returning results in seconds
Bulk resume upload and processing — drag-and-drop interface for uploading 100+ resumes at once — processing triggered automatically via AWS Lambda
Notification engine — automated alerts when a new high-match candidate is added to an active job opening — recruiter notified without needing to check manually
Client-ready shortlist export — one-click export of ranked shortlists in formatted PDF or CSV for client presentation — with match scores and candidate summaries included
Analytics dashboard — volume of resumes processed, average match scores by role, time-to-shortlist trends, and recruiter productivity metrics

Solution Architecture

The platform is built entirely on AWS serverless architecture — no servers to manage, automatic scaling with application volume, and pay-per-use pricing that keeps costs proportional to usage:

Layer	AWS Service / Technology	Role in HR Mind Platform
Ingestion	AWS S3	Secure storage for all uploaded resumes (PDF, Word, text) — triggers Lambda functions on upload for automatic processing
Document Parse	AWS Textract	Extracts structured text from PDF resumes including scanned documents — feeds clean text to the NLP pipeline
NLP / AI	AWS SageMaker + Lambda	ML models for resume classification, keyword extraction, semantic matching, and candidate scoring — deployed as serverless endpoints
Text Embeddings	Amazon Comprehend	NLP entity extraction and semantic understanding — identifies skills, job titles, organisations, and dates from unstructured resume text
Matching Engine	AWS Lambda	Serverless function orchestrating JD parsing, keyword extraction, resume-to-JD matching, and score calculation — triggered per job opening
API Layer	AWS API Gateway	RESTful API endpoints for recruiter dashboard, resume upload, JD submission, shortlist retrieval, and candidate search
Data Store	Amazon DynamoDB	NoSQL database storing structured candidate profiles, match scores, JD keyword profiles, shortlists, and recruiter actions
Auth	AWS Cognito	Recruiter and admin authentication — role-based access to platform features and candidate data
Notifications	Amazon SNS	Real-time alerts to recruiters when new high-match candidates are processed for active job openings
Monitoring	AWS CloudWatch	Performance monitoring, error alerting, Lambda invocation metrics, and cost tracking dashboards
Security	AWS WAF + IAM	Web Application Firewall protecting API endpoints; IAM roles enforcing least-privilege access to all AWS resources
Storage Archive	S3 Lifecycle Policies	Automatic archival of old resumes to S3 Glacier — cost management for long-term candidate data retention

End-to-End Workflow

Step 1 — JD Upload	Recruiter uploads or pastes the Job Description into the platform. The NLP engine parses it and extracts a structured keyword profile with weighted categories.
Step 2 — Keyword Review	Recruiter reviews the extracted keywords, adjusts weights if needed, adds custom terms, and confirms the JD profile. The AI is now primed for matching.
Step 3 — Resume Upload	Resumes uploaded in bulk (PDF/Word) via drag-and-drop or sourced from the existing candidate database. AWS S3 stores each file and triggers automatic processing.
Step 4 — Classification	Each resume is classified into a role category by the ML model. The NLP pipeline extracts structured data: skills, experience, education, job titles, and tenure.
Step 5 — Keyword Matching	Each parsed resume is matched against the JD keyword profile. Exact and semantic matches are scored. Skills gaps are identified. An overall match score (0–100) is calculated.
Step 6 — Ranking	All candidates are ranked by their composite match score. The recruiter receives a prioritised shortlist — top candidates at the top, with full score breakdowns.
Step 7 — Review & Export	Recruiter reviews the ranked shortlist, filters by threshold if needed, compares top candidates side-by-side, and exports the final shortlist for client presentation.
Step 8 — Database Update	All candidate profiles and scores are stored in DynamoDB. As new JDs are posted, stored candidates are automatically re-evaluated — making the talent pool smarter over time.

Challenges & Solutions

Resume format diversity	Resumes arrive in PDF, Word, scanned images, and plain text. AWS Textract handles all formats including scanned PDFs — ensuring no resume is unreadable by the system.
Vocabulary mismatch	Candidates and JDs use different terms for the same skill. Semantic NLP embeddings via Amazon Comprehend identify conceptually similar terms, preventing valid candidates from being missed.
Explaining AI ranking to clients	Clients needed to understand why a candidate ranked where they did. The platform generates a transparent score breakdown per candidate — every ranking decision is explainable.
Scaling for peak volume	Recruitment campaigns can generate hundreds of applications overnight. AWS Lambda’s serverless model scales to process any number of resumes in parallel with no infrastructure provisioning required.
Bias in recruitment	Automated ranking risks encoding historical bias. The scoring model is built on skills and experience alignment only — personal identifiers are excluded from all scoring calculations.
Stale candidate database	Stored resumes quickly became outdated if not re-evaluated. The platform automatically re-scores all existing candidates against each new JD — keeping the talent pool continuously active.
Multi-industry keyword sets	HR Mind operates across 8 industry verticals — each with distinct terminology. The keyword taxonomy is industry-aware, with sector-specific skill libraries built for each vertical.

Key Benefits

Resume screening time reduced by up to 90% — what took recruiters days now takes the AI minutes
Objective, explainable candidate ranking — every shortlist position is backed by a transparent score breakdown, not recruiter intuition
Semantic keyword matching eliminates vocabulary-based false negatives — valid candidates are no longer missed because they used different terminology
Bulk processing on AWS Lambda — 100+ resumes processed in parallel with no performance degradation or infrastructure cost
Continuous talent pool intelligence — stored candidate profiles are automatically re-evaluated against every new JD, turning the database into a living, searchable asset
Faster time-to-shortlist — from days to minutes — enabling HR Mind to deliver shortlists to clients faster and win more competitive mandates
Multi-industry ready — keyword taxonomies cover all 8 of HR Mind’s industry verticals, with recruiter-adjustable profiles per role type
Bias-mitigated ranking — scoring based solely on skills, experience, and JD fit — personal identifiers excluded from all ranking calculations
Fully serverless on AWS — scales automatically with application volume at zero idle cost — the platform costs nothing when not in use
Client-ready shortlist exports — formatted PDF or CSV shortlists with match scores and summaries, ready for client presentation in one click

Implementation Approach

Peritos Solutions delivered the platform in phases, with HR Mind recruiters involved at every stage to validate AI output quality against their own domain expertise:

Phase 1 — Discovery	Recruitment workflow analysis, JD structure review across 8 industry verticals, resume format audit, keyword taxonomy design, AWS architecture design
Phase 2 — Data Pipeline	AWS S3 ingestion setup, Textract PDF parsing pipeline, resume text extraction and cleaning, DynamoDB schema design for candidate and JD profiles
Phase 3 — NLP & ML Models	Resume classification model training, keyword extraction pipeline (Amazon Comprehend + custom), semantic embedding layer for vocabulary mismatch handling
Phase 4 — Matching Engine	JD keyword extraction, weighted scoring algorithm, semantic matching layer, composite ranking engine, skills gap analysis module
Phase 5 — Dashboard	Recruiter interface build — React.js frontend, API Gateway integration, bulk upload UI, ranked shortlist view, candidate comparison, export functionality
Phase 6 — Testing & Tuning	Recruiter validation of AI shortlists vs manual shortlists — model tuning to align AI output with HR Mind domain expertise; bias audit
Phase 7 — Go-Live	Production deployment on AWS, CloudWatch monitoring setup, recruiter training, hypercare support period, ongoing model improvement pipeline

Support & Next Steps

Peritos Solutions manages the AWS environment as an ongoing cloud partner — monitoring costs, model performance, and system stability. The AI models improve continuously as more resumes and JDs are processed through the platform.

Planned next phase enhancements:

Video interview analysis — AI assessment of candidate video interviews, scoring communication skills and cultural fit signals
Candidate outreach automation — automated, personalised outreach to top-ranked candidates via email and LinkedIn based on match scores
Salary benchmarking integration — match scores combined with HR Mind’s salary analysis data to provide candidates with market compensation intelligence
Real-time job board integration — automatic ingestion of applications from job boards (LinkedIn, Indeed, Naukri) directly into the AI pipeline
Client portal — direct client access to AI-ranked shortlists with the ability to provide feedback that further trains the model to client-specific preferences
Multi-language resume support — NLP pipeline extended to process resumes in French, Chinese, and other languages for HR Mind’s global operations

Looking for a Similar AI Recruitment or HR Technology Solution?

Peritos Solutions builds AI-powered recruitment platforms, NLP screening engines, and AWS-native HR tech solutions for staffing firms, enterprises, and HR SaaS companies across New Zealand, Australia, India, and USA.

info@peritossolutions.com | +64-212579909 | www.peritossolutions.com