AI Platform Engineer: Scalable Model Serving & Infra

Barlowe LLP; Greater London; On-site; GBP 70,000 - 90,000; Full time

Benefits offered by this job

Highly competitive compensation

30 days annual leave

9% company pension contributions

Comprehensive healthcare and life assurance

Lunch provided via Just Eat

Cycle-to-work scheme

Monthly company events

Job summary

Barlowe LLP is seeking a skilled Engineer for its Core AI team based in London. This role involves designing and operating platforms for AI model inference and serving, ensuring secure access to tools and data. The ideal candidate will have strong expertise in C#, Python, and Kubernetes.

Additional perks include competitive compensation, 30 days annual leave, and comprehensive healthcare benefits.

Qualifications

• Strong expertise in C# and Python, building distributed systems and platform-level software.
• Deep Kubernetes expertise, including multi-tenant cluster operations and platform extensions.
• Experience with Docker, Terraform, and CI/CD in controlled or regulated environments.
• Strong understanding of distributed systems, including networking, storage, security, and performance.
• Experience with model serving and inference infrastructure, including deployment, scaling, and optimisation of open models.
• Clear communication skills, with ability to explain complex concepts and produce high-quality technical documentation.

Responsibilities

• Designing and operating model serving infrastructure, including inference pipelines and scheduling systems.
• Building and running centralised MCP servers, ensuring secure, reliable access to enterprise tools and data.
• Owning platform reliability, performance, and scalability across Kubernetes-based infrastructure.
• Building self-service tooling and APIs to enable teams to provision and consume AI infrastructure independently.
• Integrating platform services with existing technology stacks, ensuring clear interfaces, monitoring and CI/CD.
• Evaluating and adopting open-source technologies and applying emerging best practices to improve the platform.

Skills

C#

Python

Kubernetes

Docker

Terraform

CI/CD

Tools

Prometheus

Grafana

OpenTelemetry

Job description

Barlowe LLP is seeking a skilled Engineer for its Core AI team based in London. This role involves designing and operating platforms for AI model inference and serving, ensuring secure access to tools and data. The ideal candidate will have strong expertise in C#, Python, and Kubernetes.

Additional perks include competitive compensation, 30 days annual leave, and comprehensive healthcare benefits.