Senior Backend Engineer, LLM Inference Platform
Summary
Build and optimize backend services for a large-scale LLM inference platform, focusing on latency reduction, throughput, and GPU utilization in a production environment.
J.P. Morgan is seeking a Software Engineer III to join the Firmwide LLM Serving Platform.
You will design, build, and operate backend services for scalable LLM inference, contributing to a production platform that reduces latency, increases throughput, and maximizes GPU utilization. In this role based in Greater London, you will work in an agile team, learn about model architectures, observability, CI/CD, and secure coding practices, and collaborate across engineering, product, and operations to