AI infrastructure Engineer (SRE) Amsterdam

As an AI Infrastructure Engineer (SRE) at Together, you are responsible for keeping all user-facing services and production systems running smoothly. You are a mix of a pragmatic operator and software engineer who applies sound engineering principles, operational discipline and mature automation to our business environments and codebase.

You specialize in systems (operating systems, storage subsystems, networks), while implementing best practices for availability, reliability and scalability, with diverse interests in algorithms and distributed systems.

Responsibilities:

• Participation in an on-call (PagerDuty) rotation to respond to incidents affecting availability
• Building and operating our infrastructure with Ansible, Terraform and Kubernetes to enable scaling to a large number of concurrent users
• Building monitoring systems to guarantee the highest service quality for our customers
• Design and implementation of operational processes (such as deployments and upgrades)
• Debugging production issues across all services and layers of the stack
• Identifying improvements to production architecture from reliability, performance and availability perspectives
• Planning the growth of Together AI's infrastructure