Senior Lead, AI Infra Reliability Engineer

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

Job summary

JPMorganChase is seeking a Senior Lead Software Engineer to shape and scale AI infrastructure in production. You will own end‑to‑end reliability for large language model serving stacks, work with cloud and Kubernetes deployments, and improve observability, performance, and cost efficiency.

You will lead incident response, drive design with security in mind, and collaborate across teams to deliver secure software and robust platforms for AI applications at scale.

Qualifications

• Hands-on experience designing and delivering production AI infrastructure.
• Strong Python and backend service development skills.
• Proficiency with cloud platforms and infrastructure‑as‑code tooling.
• Solid understanding of site reliability engineering practices and incident response.
• Experience hosting and serving large language models in production.

Responsibilities

• Design, develop, and deliver secure, high‑quality production software and services for AI infrastructure.
• Build backend services and APIs for reliable AI infrastructure operations.
• Operate and scale LLM serving infrastructure on cloud and on‑prem clusters.
• Implement observability across logs, metrics, and traces with dashboards and alerts.
• Lead on‑call rotations, incident triage, and post‑incident analyses.
• Automate remediation to improve platform stability and developer experience.

Skills

Python

Cloud

Site Reliability

Observability

Cost optimization

Production systems

Tools

Kubernetes

KServe/Ray Serve

Triton Inference Server

Docker

LangChain/LLM tools

Job description

JPMorganChase is seeking a Senior Lead Software Engineer to shape and scale AI infrastructure in production. You will own end‑to‑end reliability for large language model serving stacks, work with cloud and Kubernetes deployments, and improve observability, performance, and cost efficiency.

You will lead incident response, drive design with security in mind, and collaborate across teams to deliver secure software and robust platforms for AI applications at scale.