Platform Engineer

This is a Platform Engineer opportunity with a New York health tech business whose platform uses AI extraction models to process millions of clinical documents each month. The role is a hybrid of backend product engineering and infrastructure, owning the cloud infrastructure, deployments and CI/CD for a multi-tenant platform that runs across customer and company cloud environments, including GPU infrastructure for model serving. You’ll build backend services such as document pipelines, application logic and platform features, own cloud infrastructure and deployment pipelines in company and customer environments on AWS and Azure, and manage Kubernetes clusters, containerised services, releases and GPU nodes. You’ll build monitoring and observability to catch pipeline failures and data quality regressions early, debug production issues across application and infrastructure layers, and work with a largely offshore engineering team on architecture, code review and stability. The ideal candidate will have 3+ years as a platform or infrastructure engineer at a startup or growth-stage company, strong backend engineering skills and working knowledge of cloud (AWS or Azure), Kubernetes, Docker, CI/CD, networking and monitoring. The ability to switch between product coding and operations work is important. Experience with data-heavy applications, ML model serving and GPU infrastructure would be advantageous. This is a hybrid position in New York City, suited to an engineer who wants a broad remit in a small team.

Requirements