Together AI is seeking an AI Infrastructure Engineer (SRE) to keep user-facing services and production systems running smoothly. The role involves on-call rotation, building infrastructure with Ansible, Terraform, and Kubernetes, designing monitoring systems, and debugging production issues. Requires 7+ years of SRE experience and expertise in cloud services and automation tools.
Responsibilities
Be on an on-call (PagerDuty) rotation to respond to incidents that impact availability
Build and run our infrastructure with Ansible, Terraform, and Kubernetes to enable scaling to a massive number of concurrent users
Build monitoring systems to ensure the highest quality service for our customers
Design and implement operational processes (such as deployments and upgrades)
Debug production issues across all services and levels of the stack
Identify improvements for the product architecture from the reliability, performance and availability perspectives
Plan the growth of Together AI’s infrastructure
Requirements
7+ years of professional SRE or related experience
Bachelor's degree in Computer Science or a related field or equivalent work experience
Expert knowledge of Ansible (roles, playbooks), Terraform, and Kubernetes
Together AI is an AI-native cloud platform providing a full-stack infrastructure for AI development, including high-performance inference, fine-tuning, and GPU cluster management. It is designed to help AI engineers and researchers scale applications reliably and efficiently.