Senior AI Infra & LLM Platform Engineer

JP Morgan Chase; Glasgow; On-site; GBP 62,000 - 102,000; Full time

Job summary

JP Morgan Chase's AI and Machine Learning Platform team is hiring to design, build, and operate secure, production-grade AI infrastructure. You will develop backend services, host large language models, and ensure reliability and cost efficiency in cloud and on‑prem environments.

This role emphasizes observability, CI/CD, and scalable GPU/LLM workflows. The position offers full-time work in the UK, with ownership of reliability, performance, and security across the platform, and opportunities to

Qualifications

• Hands-on experience with system design, development, testing, and production stability.
• Advanced proficiency in Python for building production-grade services.
• Experience with automation, CI/CD, and IaC tooling.
• Knowledge of cloud infrastructure and container orchestration.
• Strong site reliability engineering practices: incident management, runbooks, reliability patterns.
• Practical knowledge of observability across metrics, logs, and traces.

Responsibilities

• Design, develop, troubleshoot, and deliver secure, high-quality production software and services for AI infrastructure.
• Build backend services and APIs that enable reliable operation of AI infrastructure in production environments.
• Operate and scale large language model serving infrastructure, including model hosting and routing.
• Deploy, host, and lifecycle-manage LLMs on cloud and on-premises using reproducible IaC and CD pipelines.
• Implement observability with dashboards and alerting for LLM and GPU workloads.
• Lead reliability engineering for LLM endpoints, including capacity planning and incident response.

Skills

System design

Python

Automation

Cloud platforms

IaC

SRE

Observability

Security

AI tooling

Incident management

Model serving

Team collaboration

Tools

Kubernetes

GPU clusters

CI/CD tooling

Job description

JP Morgan Chase's AI and Machine Learning Platform team is hiring to design, build, and operate secure, production-grade AI infrastructure. You will develop backend services, host large language models, and ensure reliability and cost efficiency in cloud and on‑prem environments.

This role emphasizes observability, CI/CD, and scalable GPU/LLM workflows. The position offers full-time work in the UK, with ownership of reliability, performance, and security across the platform, and opportunities to