Infrastructure Engineer

Replicate is revolutionizing AI accessibility by building the premier platform for creating, deploying, and running machine learning models. As an Infrastructure Engineer on the Platform team, you'll be at the forefront of making generative AI available to developers worldwide.

The role involves managing the complete lifecycle of ML models, from packaging and deployment to serving, scaling, and monitoring. You'll be working with a platform that supports thousands of models and handles millions of daily predictions. This position offers a unique opportunity to build innovative solutions where your decisions have direct impact.

The technical stack includes Python, Go, Node.js, Kubernetes, Terraform, and databases like Redis, Google BigQuery, and PostgreSQL. You'll be working on critical infrastructure components, including multi-regional traffic management, GPU optimization, and sophisticated task allocation systems.

The ideal candidate brings experience in platform development at scale, understanding of complex systems architecture, and proven ability with Kubernetes operations. While ML/AI production experience is a plus, the role focuses on infrastructure rather than model building. Strong communication skills are essential as you'll be collaborating closely with teams and translating complex concepts into actionable insights.

Based in Replicate's Mission district office in San Francisco, this role offers the chance to be part of building a strong in-person culture while working on cutting-edge AI infrastructure. You'll be joining a team dedicated to democratizing AI technology and making it accessible to developers everywhere.