Senior LLM Platform Reliability Engineer

慨正橡扯; Glasgow; On-site; GBP 90,000 - 130,000; Full time

Job summary

JPMorganChase is hiring a Senior Lead Software Engineer to shape AI infrastructure and ensure reliable production deployment at scale. You will own LLM serving stacks end-to-end, implement observability, and drive cost-efficient performance on cloud and on-prem GPU clusters.

You will lead reliability engineering, incident response, and continuous improvement across teams, balancing risk and delivery speed in a cutting-edge AI platform environment.

Qualifications

• Hands-on system design and production-grade software in live environments.
• Advanced Python for building services and tooling.
• Automation and continuous delivery practices.
• Cloud infrastructure and IaC tooling for lifecycle management.
• Strong site reliability engineering knowledge and incident handling.

Responsibilities

• Design, develop, troubleshoot, and deliver secure, production software for AI infra.
• Build backend services and APIs for reliable AI infrastructure operations.
• Operate and scale large language model serving infra in cloud and on-prem environments.
• Implement observability with dashboards and actionable alerts for GPU workloads.
• Lead on-call rotations, incident triage, and post-incident analyses.
• Automate remediation to improve platform stability and dev experience.

Skills

System design

Python production services

Automation & CD

Cloud infrastructure

Site reliability engineering

Observability

Kubernetes

GPU/ML infra

Incident response

AI safety practices

Tools

KServe

Ray Serve

NVIDIA Triton

LangChain

Job description

JPMorganChase is hiring a Senior Lead Software Engineer to shape AI infrastructure and ensure reliable production deployment at scale. You will own LLM serving stacks end-to-end, implement observability, and drive cost-efficient performance on cloud and on-prem GPU clusters.

You will lead reliability engineering, incident response, and continuous improvement across teams, balancing risk and delivery speed in a cutting-edge AI platform environment.