Finding a job online has become an immense task for job seekers. Companies are increasingly using generative AI to screen applicants, resulting in an imbalance between those looking for jobs and the companies that post them. Hyperleap AI set out to empower job seekers with the same level of technological sophistication that job posters have. The company transformed its traditional job board into Jennie Johnson, a generative AI–powered personalized job platform built with the help of AWS Partner Pinecone. The solution uses generative AI to match job seekers with relevant positions, resulting in a 50 percent increase in email click-through rates and scaling to over $30,000 in monthly recurring revenue. More importantly, it helps users discover better-matching opportunities and craft tailored applications, while dramatically reducing the effort required to land interviews.

Opportunity | Addressing Inequity in the Job Search Process

As traditional job boards charge a fee to job posters but are free to job seekers, they typically prioritize job posters’ needs—often leaving job seekers with generic tools and limited insight. Hyperleap AI saw an opportunity to rebalance this dynamic by building a platform that puts the job seeker first. “Big job boards are focused on the people who pay them money, which are companies,” says Alex Bowcut, chief technical officer of Hyperleap AI. “We wanted to level the playing field between big companies who are deploying generative AI for hiring—and the actual candidates.”

But solving this challenge required more than just listing jobs—it meant building an intelligent assistant that could understand resumes in context, create personalized recommendations for roles, and even automate resume customization. “People’s professional lives are more than just a bag of words,” says Bowcut. “The way that words appear, and their semantic meaning, is actually quite important when you read someone’s resume.”

Solution | Building a Personalized Platform with Generative AI on AWS

Hyperleap AI developed Jennie Johnson, a job seeker–focused platform powered by Pinecone’s serverless vector database and AWS infrastructure, to deliver personalized job recommendations and application support. By processing resumes and job descriptions using vector embeddings, Jennie Johnson can assess semantic meaning and context in resumes, matching candidates to opportunities that align with their experience—not just their keywords. “We want Jennie Johnson to feel like a very fluid product; but behind the scenes, there’s so much that goes on in order to facilitate that experience,” says Bowcut.

The solution is powered by several AWS services. The core infrastructure was built on Amazon Elastic Compute Cloud (Amazon EC2), which provides secure and resizable compute capacity for virtually any workload. For messaging, it used Amazon Simple Queue Service (Amazon SQS)—which offers fully managed message queuing for microservices, distributed systems, and serverless applications—and Amazon Simple Notification Service (Amazon SNS), a fully managed publish/subscribe service. The solution scales efficiently during peak usage times, such as while sending morning job-alert emails.

Outcome | Helping Job Seekers Land Interviews Faster

The move from full-text search to vector-based matching had a tangible impact. “We saw an over 50 percent increase in users clicking on jobs after switching from full-text search databases to vector databases,” says Bowcut.

With better-matched opportunities and generative AI–powered features like resume rewriting and custom cover letter generation, Jennie Johnson is helping users reduce the number of applications that they need to submit while also improving their chances of landing interviews. “We’ve scaled the product from nothing to over $30,000 in monthly recurring revenue,” says Bowcut. “But more importantly, I think we’ve seen a large impact in our users’ job-seeking life.”