Senior AI Platform Engineer - Scalable Inference

JPMorganChase; Glasgow; On-site; GBP 110,000 - 160,000; Full time

Job summary

J.P. Morgan in Glasgow is seeking a Senior Lead Software Engineer to shape platform standards, tooling, and production-grade ML inference foundations. You will work with large language model serving stacks and Kubernetes deployments to enable fast, reliable AI at scale.

You will mentor engineers, define automation, and collaborate with platform and product teams to improve reliability, developer experience, and operational outcomes while upholding secure, enterprise-grade engineering practices.

Qualifications

• Hands-on experience building platform tooling and CLIs.
• Deep experience with large language model inference systems.
• Experience with AWS and cloud infrastructure.
• Kubernetes deployments and scaling expertise.
• Secure coding and DevSecOps practices.
• Ability to translate architecture into secure, scalable implementations.
• Strong CI/CD and automation skills.

Responsibilities

• Lead the design and delivery of platform standards and tooling to simplify adoption and day-to-day use.
• Engineer and operate production LLM inference services using modern serving engines.
• Drive Kubernetes-based deployment patterns, scaling, networking, and troubleshooting for reliable operations.
• Optimize inference performance by understanding GPU memory behavior and bottlenecks.
• Evaluate inference-time quantization trade-offs for latency, throughput, and cost.
• Implement secure, high-quality production code and automation to improve resiliency and observability.
• Establish architecture/design artifacts and enforce non-functional requirements via automation.
• Promote enterprise AI-assisted engineering practices and reusable patterns across the team.
• Apply SDLC tools and AI-assisted development capabilities to improve automation value.

Skills

LLM inference

Kubernetes

Cloud AWS

Platform tooling

Performance tuning

Security & resilience

CI/CD & automation

Tools

vLLM

TensorRT-LLM

SGLang

LLM-D

Docker

Job description

J.P. Morgan in Glasgow is seeking a Senior Lead Software Engineer to shape platform standards, tooling, and production-grade ML inference foundations. You will work with large language model serving stacks and Kubernetes deployments to enable fast, reliable AI at scale.

You will mentor engineers, define automation, and collaborate with platform and product teams to improve reliability, developer experience, and operational outcomes while upholding secure, enterprise-grade engineering practices.