About the job

AI Engineer

📍 London Hybrid (2 days onsite)

📅 6 Month Contract

💷 Outside IR35

We're partnering with a market-leading technology-driven organisation that is investing heavily in AI-first software engineering practices and looking for an exceptional AI Engineer to join a high-performing engineering team.

This is not a traditional software engineering role.

You'll be working at the forefront of AI-assisted development, helping shape an environment where AI agents are responsible for the majority of code generation whilst engineers focus on architecture, specification, governance, review quality and production outcomes.

The Opportunity

As an AI Engineer, you'll be responsible for designing, building and improving the frameworks, tooling and guardrails that enable engineering teams to safely and effectively develop software with AI.

You'll work across the entire development lifecycle, from specification and context engineering through to deployment, optimisation and production monitoring.

This role is perfect for someone who has already built and shipped AI-powered products into production and understands the challenges that come with reliability, evaluation, governance, latency and cost management.

Key Responsibilities

• Build and deliver AI-powered product features using modern LLM architectures.
• Define detailed technical specifications that AI agents can execute against effectively.
• Create and maintain high-quality engineering documentation, standards and conventions.
• Improve developer productivity by removing friction from build, testing and deployment processes.
• Develop reusable AI tooling, frameworks, skills, sub-agents and shared engineering capabilities.
• Establish best practices and governance for reviewing AI-generated code.
• Implement robust evaluation frameworks, testing strategies and production monitoring.
• Continuously optimise AI workflows for quality, performance, cost and scalability.
• Drive adoption of AI-enabled software engineering practices across the wider team.
• Operate in a fast-moving environment focused on rapid iteration and continuous improvement.

Required Experience

We're looking for engineers who have successfully delivered AI products into production rather than purely experimental or proof-of-concept work.

You should have experience with:

• Building and deploying LLM-powered applications at scale.
• Tool calling, structured outputs, streaming responses and agent workflows.
• Evaluation frameworks, testing harnesses and AI quality measurement.
• Retrieval Augmented Generation (RAG) and context engineering techniques.
• Diagnosing retrieval, reasoning and generation failures.
• Production monitoring, optimisation and observability.
• Cost management, token optimisation and model routing.
• Multi-step agent workflows and autonomous systems.
• Designing secure AI systems with appropriate governance and controls.
• Working within regulated or compliance-sensitive environments.

Desirable Experience

• MCP (Model Context Protocol) server development.
• Durable agent execution and orchestration platforms.
• AI infrastructure engineering.
• Building internal AI developer platforms and tooling.
•