AI Platform Engineer: Scale LLMs & RAG on Azure (Onsite)

Morson Edge; Nottingham; Presencial; GBP 90 000 - 110 000; Tempo integral

Resumo da oferta

Morson Edge in Manchester is seeking an AI Platform Engineer to build, optimise and maintain scalable cloud-native infrastructure behind a growing portfolio of AI-powered apps. You will focus on LLMs, RAG and AI workloads, delivering production-grade services in a fast-moving environment.

The role requires strong Python development, hands-on Azure experience, and expertise with data pipelines, vector databases and IaC.

Qualificações

• Strong Python development skills.
• Commercial experience delivering solutions using Microsoft Azure.
• Experience with data integration and ETL pipelines (e.g., Azure Data Factory).
• Familiarity with vector databases or search technologies (OpenSearch).
• Experience with Terraform, IaC and containerised applications.
• Understanding of APIs, microservices and cloud-native architecture.
• Experience supporting production systems with focus on scalability and performance.

Responsabilidades

• Design, build and optimise production-grade AI platforms, RAG pipelines and LLM integrations.
• Develop scalable cloud-native services and backend infrastructure using Microsoft Azure.
• Improve the performance, reliability and latency of AI applications and retrieval workflows.
• Manage infrastructure-as-code using Terraform and support containerised deployments.
• Build CI/CD pipelines and automate data ingestion, embedding generation and vector indexing.
• Implement monitoring, logging, tracing and performance optimisation across AI workloads.
• Apply security, access controls, versioning and governance best practices.
• Collaborate with AI, software engineering, DevOps and security teams to deliver production-ready solutions.

Conhecimentos

Python

Azure

ETL pipelines

Vector databases

Terraform

IaC

APIs & microservices

Ferramentas

OpenSearch

Descrição da oferta de emprego

Morson Edge in Manchester is seeking an AI Platform Engineer to build, optimise and maintain scalable cloud-native infrastructure behind a growing portfolio of AI-powered apps. You will focus on LLMs, RAG and AI workloads, delivering production-grade services in a fast-moving environment.

The role requires strong Python development, hands-on Azure experience, and expertise with data pipelines, vector databases and IaC.