Infrastructure Engineer

About the Role

You will build and own the infrastructure that powers our company. This role is essential to supporting the massive workloads of our customers and enabling our system to scale to billions of agents. You will manage our GPU and AWS infrastructure, improve our runtime optimization, build dedicated endpoints, enforce security, and ensure efficient use of compute. Today we run on AWS, SST, and Modal for GPUs. You will establish best practices and set the foundation for long-term scalability.

In this role, you will:

• Design and manage infrastructure to support large-scale AI workloads.
• Optimize GPU utilization, scheduling, and scaling.
• Improve runtime performance and build dedicated endpoints for customer workloads.
• Implement robust security and reliability practices across the system.
• Establish best practices for deployment, monitoring, and operations.
• Ensure efficient use of compute to keep inference costs low.

You might thrive in this role if you:

• Have managed large-scale cloud infrastructure, ideally on AWS.
• Have deep experience with GPUs, containers, and distributed systems.
• Have built or optimized systems for high performance and cost efficiency.
• Have worked on security and reliability in production environments.
• Enjoy designing long-term infrastructure but can also move quickly in a startup environment.
• Want ownership over a critical system that determines how billions of agents will run.

Location

We are based in Boston, MA, and are in the office 5 days a week. For an exceptional candidate, we are willing to consider remote work.

Compensation

We can't build this company without you, and we want you to be a meaningful owner alongside us. So far, "Hongyin, Jack, Wei, and Dana" built the company, but a few months after you join we will have built the company together. Your equity will reflect that.

Salary will be between $170k-$220k with significant equity ownership.