Full-Stack Engineer

Replicate is looking for a Full-Stack Engineer to help us build the infrastructure that makes machine learning feel like magic. You will work across the entire stack—from high-performance dashboard interfaces to the orchestration layers that manage thousands of GPUs and open-source models. Your work will directly impact how hundreds of thousands of developers deploy, scale, and interact with state-of-the-art AI.

- Build and maintain the web platform where users discover, run, and deploy machine learning models via the browser and API. - Design and implement robust, typed APIs that serve as the interface between our users and our GPU orchestration layer. - Improve the performance and developer experience of the Replicate dashboard and public model pages. - Collaborate with the Infrastructure and ML teams to build tooling for visualizing model outputs and monitoring deployments. - Participate in an on-call rotation to ensure the reliability of a platform that processes millions of predictions daily. - Write high-quality, maintainable code and provide thoughtful feedback during peer code reviews. - Directly engage with the community to identify friction points in the developer workflow and build solutions.

- 5+ years of experience building and scaling high-traffic web applications in a production environment. - Strong proficiency with Go or Python, and recent professional experience with React and Next.js. - Deep understanding of modern web standards, API design, and asynchronous architectural patterns. - Experience working with PostgreSQL and high-scale data modeling. - Comfort working in a fast-paced, 100% remote startup environment with high autonomy. - A strong product sense and the ability to think from the developer's perspective. - Familiarity with Docker and containerization basics.