InterWiz Achieves 90% AI Cost Reduction with Amazon Bedrock
Discover how InterWiz leveraged Amazon Bedrock to cut AI costs drastically, improve efficiency, and secure a competitive edge in the recruitment industry.
Key Facts
- InterWiz cut AI costs by 90%, transforming profitability from $27,000 savings annually.
- 55% latency improvement enhances candidate experience, boosting retention and satisfaction rates.
- Multi-provider architecture ensures 99.9% uptime, reducing risk of service disruptions significantly.
- Flexibility to adopt new models rapidly positions InterWiz ahead of competitors in innovation.
- AWS Partner Network access lowers migration costs, enhancing financial viability for AI startups.
Summary
Summary
InterWiz, an AI-powered recruitment company, faced skyrocketing AI infrastructure costs that threatened their growth. By migrating their AI workloads to Amazon Bedrock with the help of Emumba, they achieved a 90% reduction in AI costs, improved response times by 55%, and maintained 99.9% uptime without service disruption.
Background
InterWiz operates in the recruitment industry, automating candidate screening through AI-driven interviews. Prior to the deployment, they were conducting over 1,000 interviews monthly, but their AI expenses consumed 40% of their per-interview revenue, making aggressive growth unprofitable.
Challenge
InterWiz needed to address rising AI costs that limited their ability to scale and compete effectively. Their existing infrastructure was tied to a single AI provider, which restricted their model choices and resulted in high operational costs.
Solution
Emumba, an AWS Advanced Tier Services Partner, led the migration to Amazon Bedrock using a systematic seven-phase methodology. This included assessing models, optimizing prompts, and progressively rolling out the new architecture. They evaluated multiple foundation models and designed a specialized architecture that assigned interview functions to the most suitable models.
Results
The migration, completed over a structured 3-month timeline, yielded significant outcomes:
- AI costs dropped from $0.25 to $0.025 per interview, resulting in an annual savings of $27,000 as InterWiz scales to 10,000 interviews monthly by 2026.
- Response times improved from 850 milliseconds to 450 milliseconds, enhancing the candidate experience.
- Uptime was maintained at 99.9% through a multi-provider architecture.
Key Insights
The InterWiz case highlights the importance of architectural flexibility and model choice in AI deployments. Companies can achieve cost predictability and competitive advantages by evaluating multiple models and adapting quickly to new innovations.
Customer Testimonial
“Migrating our AI stack from Azure OpenAI to Amazon Bedrock was a complex undertaking, but AWS CoE at Emumba handled it with precision and engineering depth. They built the abstraction layers, tuned our prompts, and managed rollout risks so thoroughly that we experienced no disruption, only improvement. The new setup is faster, cheaper, and far more scalable. We couldn’t have asked for a smoother transition.” — Zishan Iqbal, CEO, InterWiz AI
Entities Mentioned
Companies
Products
Technologies
People
Organizations
Key Concepts
Definitions
- Amazon Bedrock
- A service that provides access to high-performing foundation models through a single API for building generative AI applications.
- Foundation Models (FMs)
- Large AI models that can be adapted for various tasks, providing a base for building specific applications.
- AWS Partner Network
- A global program that helps partners build successful AWS-based businesses by providing resources and support.
- Generative AI
- A type of AI that can generate new content, such as text or images, based on learned patterns from existing data.
- Latency
- The time delay between a user's action and the system's response, critical in real-time applications like interviews.
Use Cases
- →Automated candidate screening
- →AI-driven interviews
- →Cost-effective scaling of AI workloads
- →Real-time candidate evaluations
- →Prompt optimization for AI models
- →Multi-provider architecture for service continuity
Frequently Asked Questions
How did InterWiz reduce its AI costs?
InterWiz reduced its AI costs by migrating to Amazon Bedrock, which allowed them to leverage multiple foundation models and optimize their AI workloads. This migration led to a 90% reduction in AI expenses per interview.
What benefits did Emumba provide during the migration?
Emumba provided expertise in AWS services, access to funding programs, and a proven migration framework that minimized risks. Their systematic approach ensured a smooth transition without service disruptions.
What improvements were observed post-migration?
Post-migration, InterWiz experienced a 55% improvement in response times and maintained 99.9% uptime. These enhancements contributed to a better candidate experience during interviews.
Why is multi-model flexibility important?
Multi-model flexibility allows companies to choose the best foundation model for specific tasks, enhancing performance and cost efficiency. It also enables quicker adoption of new models as they become available.
How does Amazon Bedrock support compliance?
Amazon Bedrock is designed to meet compliance requirements for regulated industries, including HIPAA and GDPR. It provides necessary controls and support for organizations to maintain compliance while using its services.