AI-Powered Candidate Screening & Ranking Agent
Hire me Club — Agentic AI Recruitment Platform
Hire me Club — Agentic AI Recruitment Platform
Mist Avinya Technologies LLP designed and deployed a fully serverless Agentic AI recruitment platform on AWS, enabling Hire me Club to automate candidate screening, improve recruiter efficiency, and scale hiring operations using Amazon Bedrock Agents and Claude 3.5 Sonnet.
Hire me Club is an SMB HR technology company operating in the recruitment sector, delivering sourcing, screening, shortlisting, and onboarding services for mid-market employers across multiple industries.
The organization processes between 800 to 1,200 candidate CVs per open role while operating with a lean recruitment team. Manual candidate screening created operational bottlenecks, slowing down recruiter productivity and delaying candidate engagement.
Recruiters spent most of their time reviewing resumes manually, limiting the company's ability to scale during peak hiring periods.
The engagement focused on reducing recruiter workload, accelerating shortlist delivery, and introducing AI-driven screening consistency while maintaining auditability and human oversight.
Reduce candidate shortlist generation from 5–7 business days to under 24 hours for standard recruitment roles.
Reduce recruiter time spent on CV screening by at least 60%, allowing teams to focus on candidate engagement and hiring decisions.
Implement AI-based scoring and ranking to reduce inconsistencies and improve compliance across recruitment workflows.
Support three times peak hiring volume without increasing operational headcount.
Mist Avinya implemented a fully autonomous Agentic AI candidate screening platform using Amazon Bedrock Agents integrated with the customer's Applicant Tracking System (ATS).
The solution was built using a secure, scalable, and serverless AWS architecture optimized for enterprise-grade AI operations.
Core orchestration layer handling agent reasoning, tool invocation, workflow sequencing, and session management.
Foundation model used for candidate evaluation, multi-step reasoning, scoring, and justification generation.
Extracted structured text from uploaded CVs, including scanned PDF and DOCX documents.
Stored job descriptions, scoring rubrics, candidate evaluations, audit trails, and agent logs.
Powered all Bedrock Agent tools using isolated, least-privilege serverless functions.
Securely stored candidate CVs and processed documents with versioning and object locking enabled.
Security, governance, and responsible AI practices were integrated throughout the entire solution architecture.
The AI-powered recruitment platform delivered measurable operational improvements within the first three months after deployment.
The solution was designed using a fully serverless AWS-native architecture focused on scalability, resilience, security, and operational simplicity.
All AWS services including Amazon Bedrock Agents, AWS Lambda, Amazon S3, DynamoDB, SNS, Textract, and API Gateway are deployed across multiple Availability Zones with no single point of failure.
The architecture supports dynamic scaling using serverless services, Lambda concurrency scaling, Bedrock on-demand inference, and Step Functions fan-out orchestration for high-volume recruitment workloads.