Backend Infrastructure Engineer

Sesame•San Francisco, CA

20d

About The Position

As a Backend Infrastructure Engineer at Sesame, you will work across the stack, with an emphasis on backend, infrastructure, and systems. You should feel comfortable working on any typical software project, with the ability to quickly learn new tools and services with a strong intuition on software development and software deployment best practices.

Requirements

Ability to set, own, and communicate direction.
Hands-on reliability engineering experience. You hold convictions about monitoring and observability methodology, deployment systems, loosely coupled components, etc.
Experience shipping services at scale.
Experienced systems designer in designing and shipping flexible domain models and APIs.
A track record of delivering efficiency through automation.
Experience solving challenging infrastructure problems (using the tools below).

Nice To Haves

Significant IaC experience (Terraform preferred).
CloudFormation, Pulumi, Kube-based, etc.
Architected a multi-stack, self-serve Terraform system, or maintained one.
Understand the challenges of building infrastructure at scale.
Significant Kubernetes experience.
Some ML experience.
Torch experience, especially model optimization for serving.
General ML training or serving experience.
Built ML serving and/or training infrastructure.
Experience in Torch Serve, Seldon, KServe, Ray Serve, etc.
Experience building large-scale distributed training and serving systems.
Data engineering experience.
Technical leadership.
Database design.
Real-time communication experience.

Responsibilities

Build a secure, maintainable, self-serve core infrastructure.
Build a modern training architecture and a modern serving architecture.
Build and scale a low-latency voice interface and audio processing pipeline.
Build low maintenance, high leverage developer tooling, server, and data infrastructure.