Architecture for IT Internship Recruitment Process Based on AWS Cloud

Abstract

Introduction: The current recruitment processes face challenges due to lack of automation and scalability. Filtering student data manually is both time-intensive and prone to errors. Managing high volumes of applications securely is difficult, and there is limited capability to effectively track applications and notify students.

Objectives: This paper aims to design a secure, automated, and scalable cloud application on Amazon Web Services (AWS) leveraged by NLP-based deep learning models like Bidirectional Encoder Representations from Transformers (BERT) and Sentence Transformer to streamline Information Technology (IT) internship recruitment using Amazon S3 + CloudFront, AWS WAF, API Gateway, AWS Step Functions, AWS Lambda, Amazon RDS, AWS SNS, and CloudWatch.

Methods: AWS’s functions as well as powerful machine learning tools were utilized for the recruitment process automation and streamlining. We present BERT fine-tuning results on the research tasks by employing datasets such as (1) Stanford Question Answering Dataset (SQuAD v1.1), (2) SQuAD 2.0, (3) General Language Understanding Evaluation (GLUE) benchmark, and (4) Situations With Adversarial Generations (SWAG) dataset.

Results: With SQuAD v1.1, our proposed AWS-based method obtained 88.1 (EM) and 95.1 (F1) for Dev, and 90.1 (EM) and 95.2 (F1) for Test. With SQuAD v2.0, our proposed AWS-based method obtained 83.2 (EM) and 86.3 (F1) for Dev, and 83.4 (EM) and 88.4 (F1) for Test. Our proposed AWS-based method obtained 88.9 (Dev) and 88.8 (Test) for SWAG Dev and test accuracy.

Conclusions: The solution provided by our proposed method simplifies the recruitment process, strengthens security through AWS services, scales effortlessly to manage high volumes of applications, automates notifications for better communication, provides administrators with convenient access to recruitment data, offers a cost-efficient and fully managed cloud-based infrastructure.