Quality Engineer - AI Platform Engineering

Employment Type: Inside IR35 Contract

Duration: 6 Months

Rate: £650 - £750/ Day

Location: Central London, Hybrid (3 Days Onsite per Week)

Opportunity Overview

A global organisation is building a centralised AI enablement and platform engineering function focused on delivering scalable, secure, and governed AI capabilities across the enterprise.

This role sits within a programme delivering enterprise-grade agentic AI infrastructure, including internal AI assistants, retrieval and search services, extensibility frameworks, and governance tooling.

Programme Overview

The programme is focused on delivering a production-grade internal agentic AI platform, including:

• Development of an enterprise AI assistant capable of reasoning, planning, and tool orchestration
• Operation of enterprise retrieval, search, and grounding services for approved data sources
• Delivery of a secure internal gateway layer providing discovery, observability, policy enforcement, and lifecycle management for AI-integrated services
• Design and development of AI-integrated services and reusable capabilities that safely expose internal and third-party systems to AI agents
• Establishment of evaluation, governance, and quality-control frameworks to support scalable and compliant deployment of AI capabilities

The programme currently follows a centrally delivered model while evolving towards a federated contribution approach over time.

Key Responsibilities

• Define and implement evaluation frameworks covering correctness, safety, reliability, and regression impact for AI-integrated services
• Develop and maintain automated test pipelines for agentic workflows, including tool orchestration and multi-step execution paths
• Identify, evaluate, and mitigate AI system failure modes such as hallucinations, invalid inputs, latency issues, and inappropriate tool usage
• Produce testing and governance evidence required for internal approval and operational processes
• Collaborate closely with ML Engineers and platform teams to embed testability and evaluation capabilities into AI services
• Contribute to the long-term quality assurance and governance strategy for enterprise-wide AI platform adoption

Essential Skills and Experience

• Strong Python development experience, particularly for automation and test frameworks
• Experience with LLM and RAG evaluation tooling, frameworks, or custom evaluation pipelines
• Expertise in automated testing across unit, integration, and regression testing environments
• Good understanding of agentic AI systems, associated risks, and operational failure modes
• Ability to assess technical solutions against governance, audit, and security requirements
• Experience working within regulated or highly governed engineering environments

What's on Offer

• Opportunity to contribute to large-scale enterprise AI transformation initiatives
• Exposure to cutting-edge AI platform engineering and governance challenges
• Collaborative environment working alongside platform engineers, ML specialists, and architecture teams
• Influence over the development of long-term AI quality and governance standards
• Opportunity to shape scalable AI engineering practices within a complex enterprise environment