Staff AI Engineer - AI Transformation

Salary: £67,000 - 107,000 per year

Requirements:

• You have shipped multi-agent systems or complex AI products to real users.
• You understand context management, including retrieval strategies, chunking, conversation memory, summarisation, and related cost/quality trade-offs.
• You have experience with model selection and routing based on capability, latency, cost, and reliability.
• You understand cost engineering for production AI systems, including token economics, caching, prompt optimisation, and batching.
• You have experience designing tool use and agent augmentation, including failure handling and MCPs or equivalent interfaces.
• You have built multi-agent coordination systems with task decomposition, handoff protocols, shared state management, and orchestration logic.
• You have built evaluation and quality frameworks for AI output, including automated pipelines and human-in-the-loop review.
• You can own problems from user need to production system and work with a founder mindset.
• You build with Claude Code daily, set context and constraints before generating code, and review AI output critically.
• You work across the stack, including LLM integration, backend services, data pipelines, and enough frontend to ship end to end.
• You can communicate technical strategy clearly to cross-functional stakeholders and document decisions.
• Experience in EdTech, regulated content, or domains where AI output quality has compliance or accreditation implications would set you apart.
• Background as a founding engineer or technical co-founder would set you apart.
• Published thinking or external contributions in AI engineering would set you apart.
• Experience designing platform layers that other teams build on would set you apart.
• Practical experience with MCP or equivalent agent integration standards would set you apart.

Responsibilities:

• Own the architecture of our internal agentic operating system, including agent orchestration, context strategy, tool integrations, evaluation framework, and production operation.
• Ship production AI agent systems by writing code, reviewing code, and owning the quality of what goes to production.
• Design multi-agent coordination patterns, including task decomposition, handoff protocols, shared state management, and orchestration logic.
• Build the evaluation and quality infrastructure, including automated eval pipelines, human-in-the-loop review systems, regression testing, and domain-specific quality metrics.
• Drive cost engineering through token economics, caching strategies, model routing, and prompt optimisation.
• Build the integration layer that makes existing Multiverse systems agent-accessible through APIs, MCPs, shared data contracts, and related tooling.
• Set patterns for prompt management, retrieval, guardrails, and testing through code, documentation, and architectural decisions.
• Mentor the team through code review, architectural guidance, and pairing on the hardest problems.
• Work closely with the wider engineering org and the teams whose work you are helping to reinvent.
• Explain technical strategy, discuss trade-offs, and represent the teams technical approach in cross-functional forums.
• Document decisions, not just code.

Technologies:

• AI
• Backend
• Claude Code
• Frontend
• Support
• LLM
• MCP
• Model Training
• Product Manager

More:

We are Multiverse, the upskilling platform for AI and tech adoption, and we have partnered with 1,500+ companies to transform workforce learning. Our apprenticeships help people of any age and career stage build critical AI, data, and tech skills, and our learners have driven $2bn+ ROI for employers. In April 2026, we announced $70 million in strategic funding led by Schroders Capital, with participation from StepStone Group, Lightspeed Venture Partners and General Catalyst, bringing us to a $2.1bn valuation as Europes first EdTech double unicorn. We have 800+ employees, a strong operational footprint, and ambitious plans to keep scaling. This role is based in London with a hybrid working model, and we offer benefits including 27 days of holiday plus additional days off, private medical insurance, wellbeing support, gym membership, life insurance, a work-from-anywhere allowance of up to 10 days per year, and regular team connection time. We are an equal opportunities employer and are committed to safeguarding and promoting the welfare of our learners.

last updated 36 week of 2026