Senior AI/ML Platform Engineer - LLM Inference

JPMorganChase in London seeks a Software Engineer III to join the Firmwide LLM Serving Platform team. You will build core backend services for LLM inference, optimize latency, and operate production systems at scale.

This role blends infrastructure and ML concepts: you won't need to be an ML researcher but will work across APIs, CI/CD, and tooling to deliver reliable services with strong observability and secure practices.