AI Platform Engineer - LLMs, RAG & Azure

Morson Group; Manchester; On-site; GBP 90,000 - 110,000; Full time

Job summary

Morson Group in Manchester City Centre is seeking an AI Platform Engineer to build, optimise and maintain the infrastructure behind a growing portfolio of AI-powered applications. You’ll focus on developing scalable, reliable services supporting large language models (LLMs), retrieval-augmented generation (RAG), intelligent search and conversational AI.

You’ll take ownership of existing solutions while helping bring new AI capabilities into production.

Qualifications

• Strong Python development skills.
• Experience delivering solutions on 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 apps.
• Understanding APIs, microservices and cloud-native architecture.
• Experience supporting production systems focusing on scalability, reliability and performance.

Responsibilities

• 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 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.

Skills

Python

APIs

Microservices

Cloud-native architecture

Performance optimization

Tools

Microsoft Azure

Azure Data Factory

Terraform

OpenSearch

Job description

Morson Group in Manchester City Centre is seeking an AI Platform Engineer to build, optimise and maintain the infrastructure behind a growing portfolio of AI-powered applications. You’ll focus on developing scalable, reliable services supporting large language models (LLMs), retrieval-augmented generation (RAG), intelligent search and conversational AI.

You’ll take ownership of existing solutions while helping bring new AI capabilities into production.