Senior AI Platform Engineer: Scale, Reliability & Azure Foundry

The Portfolio Group; United Kingdom; On-site; GBP 90,000 - 130,000; Full time

Job summary

The Portfolio Group is hiring an AI Platform Engineer in the United Kingdom to design, build, and run the AI platform underpinning our conversational assistant and broader AI initiatives.

You'll own runtime, infrastructure, and operational foundations for RAG pipelines, LLM orchestration, and vector search across Azure and Foundry, turning prototypes into production services with AI Engineering, DevOps, and Info-Sec.

Qualifications

• Proven enterprise delivery on Microsoft Azure.
• Experience with Azure Data Factory for ETL workflows.
• Familiarity with vector databases or search engines such as OpenSearch.
• Strong Python skills.

Responsibilities

• Build and extend a scalable AI platform via Microsoft Foundry.
• Own and optimise Foundry solutions for accuracy, scale, and latency.
• Harden the production RAG pipeline, covering inference, retrieval, and ingestion.
• Architect Azure services using Terraform infrastructure-as-code.
• Scale vector database and embedding pipelines.
• Build end-to-end observability across latency, throughput, cost, and system health.
• Strengthen resilience through fault-tolerance, caching, and autoscaling.
• Maintain CI/CD pipelines through GitHub and Azure DevOps.
• Automate embedding generation and knowledge base synchronisation.
• Embed secure-by-design principles, including IAM, encryption, and safe data flows.
• Mature governance practices, including versioning, audit logging, and compliance.

Skills

Azure platform

Python

Terraform

Containerisation

Observability

API design

Cloud-native

Tools

GitHub

Azure DevOps

OpenTelemetry

Terraform IaC

Job description

The Portfolio Group is hiring an AI Platform Engineer in the United Kingdom to design, build, and run the AI platform underpinning our conversational assistant and broader AI initiatives.

You'll own runtime, infrastructure, and operational foundations for RAG pipelines, LLM orchestration, and vector search across Azure and Foundry, turning prototypes into production services with AI Engineering, DevOps, and Info-Sec.