Lead LLM Infra & Reliability Engineer

JPMorganChase; Glasgow; On-site; GBP 90,000 - 130,000; Full time

Job summary

JPMorgan Chase in Glasgow, United Kingdom, is seeking a Lead Software Engineer to build and operate large language model serving infrastructure at scale. You will own reliability, performance, and cost‑efficiency of the LLM platform end to end, and work hands‑on with cloud and Kubernetes deployments.

You will deploy and manage LLM serving stacks (vLLM, llm-d) on Amazon EKS, SageMaker and on‑prem GPUs, with strong observability, incident response, and cost‑aware performance tuning to deliver

Qualifications

• Strong software engineering and production stability in AI systems.
• Hands-on Python for building production-grade services and tooling.
• Experience with AWS and Terraform for infra delivery.
• Knowledge of observability, monitoring, and incident response.

Responsibilities

• Design, develop, and deliver secure, high-quality production software for AI infra.
• Operate and scale LLM serving infra including model hosting and routing.
• Implement observability with dashboards and alerting.
• Lead incident response and post-incident analysis.
• Collaborate across teams to improve stability and cost efficiency.

Skills

Python

AWS

Terraform

Kubernetes

SRE

LLM inference

Observability

Tools

vLLM

llm-d

KServe

SageMaker

EKS

Prometheus

Grafana

Job description

JPMorgan Chase in Glasgow, United Kingdom, is seeking a Lead Software Engineer to build and operate large language model serving infrastructure at scale. You will own reliability, performance, and cost‑efficiency of the LLM platform end to end, and work hands‑on with cloud and Kubernetes deployments.

You will deploy and manage LLM serving stacks (vLLM, llm-d) on Amazon EKS, SageMaker and on‑prem GPUs, with strong observability, incident response, and cost‑aware performance tuning to deliver