Senior AI Infra Engineer – LLM Ops & Reliability

JPMorgan Chase & Co.; Auchentibber; On-site; GBP 90,000 - 150,000; Full time

Job summary

JPMorganChase is seeking a Senior Lead Software Engineer to shape reliable AI infrastructure at scale. You will own LLM serving stacks, optimize performance and costs, and lead incident response across cloud and on-prem GPU clusters.

The role emphasizes secure software delivery, observability, and strong engineering fundamentals. You will collaborate with engineering to deliver scalable AI platforms, drive reliability, and build reusable patterns for robust production deployments, with a focus

Qualifications

• Production-grade Python development experience with strong tooling.
• Solid cloud infrastructure exposure and CI/CD practices.
• Hands-on Kubernetes and container orchestration knowledge.
• Experience with observability, metrics, logs, traces, and alerting.

Responsibilities

• Design, develop, and deliver secure, high-quality production software for AI infra.
• Build backend services and APIs enabling reliable AI infrastructure in production.
• Operate and scale LLM serving infra on cloud and on-prem GPU clusters.
• Implement observability and cost-aware performance tuning for workloads.
• Lead on-call, incident triage, root-cause analyses, and post-incident actions.
• Automate remediation and improve platform stability and developer experience.
• Contribute to enterprise AI practices, secure coding, and testing standards.

Skills

Python

Cloud platforms

Kubernetes

Observability

Reliability engineering

Cost optimization

AI infra

Incidents management

Tools

KServe

Ray Serve

Triton

LangChain

Job description

JPMorganChase is seeking a Senior Lead Software Engineer to shape reliable AI infrastructure at scale. You will own LLM serving stacks, optimize performance and costs, and lead incident response across cloud and on-prem GPU clusters.

The role emphasizes secure software delivery, observability, and strong engineering fundamentals. You will collaborate with engineering to deliver scalable AI platforms, drive reliability, and build reusable patterns for robust production deployments, with a focus