Lead AI Platform Engineer - Scale, Observability, AI Ops

The Portfolio Group; Manchester; On-site; GBP 90,000 - 120,000; Full time

Job summary

The Portfolio Group in Manchester is seeking an AI Platform Engineer to design, build, and operate the AI platform that underpins our conversational assistant and broader AI initiatives. You will take responsibility for the runtime, infrastructure, and operational foundations underpinning our RAG pipelines, LLM orchestration, and vector search, built across Microsoft Azure and Microsoft Foundry.

Where prototypes and proof-of-concepts exist, you will be the one turning them into resilient,

Qualifications

• Proven enterprise delivery on the Azure stack.
• Experience with data pipelines and AI platforms is a plus.
• Familiarity with vector databases or search engines (e.g., OpenSearch).

Responsibilities

• Build and extend a scalable AI platform via Foundry.
• Own and optimise Foundry solutions for accuracy, scale and latency.
• Harden the production RAG pipeline for inference, retrieval and ingestion.
• Scale vector databases and embedding pipelines.
• Build end-to-end observability across latency, throughput and cost.
• Maintain CI/CD pipelines via GitHub and Azure DevOps.
• Automate embedding generation and knowledge base syncing.

Skills

Azure cloud

OpenSearch / vector DB

Terraform

Containerisation

Microservices

API design

Observability (OpenTelemetry)

Production infra ownership

AI platform experience

Tools

GitHub

Azure DevOps

OpenTelemetry

Job description

The Portfolio Group in Manchester is seeking an AI Platform Engineer to design, build, and operate the AI platform that underpins our conversational assistant and broader AI initiatives. You will take responsibility for the runtime, infrastructure, and operational foundations underpinning our RAG pipelines, LLM orchestration, and vector search, built across Microsoft Azure and Microsoft Foundry.

Where prototypes and proof-of-concepts exist, you will be the one turning them into resilient,