Test and Deploy Production Models: Automate model testing and validation. Implement and operate CI/CD pipelines to enable safe, repeatable deployments and rollbacks.
Operate Inference Services: Provision and manage backend resources for inference (compute, containers, scaling), and tune performance, reliability, and cost in production.
Monitor Model Health and Performance: Define and continuously monitor health and performance metrics for deployed services. Triage issues by severity and drive timely resolution, including incident response and runbooks.
REST API Integration: Own end-to-end REST API integration, connecting backend model services to product and platform surfaces through scalable, containerized services.
Product Ownership and Cross-functional Collaboration: Work with researchers, evaluation engineers, product managers, and partner engineering teams to deliver production-ready solutions, communicate st...