Principal AI Engineer

What You’ll Do

• Own the AI agent architecture. Design the orchestration layer, memory and context management, evaluation framework, and integration APIs that all agent products build on. Your decisions are the ones others build on top of.
• Ship production agents. You write and review code and own what goes to production. You’ll personally deliver at least one major agent system in your first six months.
• Set the engineering standard. Define how Multiverse builds with AI — evaluation methodology, multi‑agent coordination patterns, tool design, guardrails, and observability. You author the decision records and hold the bar.
• Build the integration layer. Create the APIs, MCPs, and shared data contracts that connect agents to Multiverse’s platform, content systems, and internal tools — working closely with London engineering teams who own those systems today.
• Drive technical strategy. Translate product and business goals into a coherent AI engineering roadmap. Shape which problems we tackle, in what order, and why — then socialise it with engineering leadership and the exec team.
• Raise the bar around you. You’re not a line manager, but your presence makes the engineers you work with measurably better. Code review, pairing on hard problems, setting the standard for what ‘good’ looks like in AI‑native engineering.

You’ve shipped multi‑agent systems to real users. You understand context management, model selection and routing, cost engineering (token economics, caching, prompt optimisation), tool use and failure handling, multi‑agent coordination, and evaluation frameworks for non‑deterministic systems. This is depth, not familiarity.

You’ve set technical direction across multiple teams, not just within a single squad. You translate complex architecture decisions into business‑relevant narratives for executive stakeholders. You’ve defined engineering standards that were adopted organisation‑wide — not just recommended, but embedded.

You work across the stack — LLM integration, backend services, data pipelines, and enough frontend to ship end‑to‑end. You build with Claude Code daily, critically review AI output, and augment your tools with context and constraints to make them effective.

You don’t wait to be handed a roadmap. You identify which problems are worth solving, in what order, and why — and you make the case for building before anyone asks you to.

• Background as a founding engineer or technical co‑founder
• Experience in EdTech, regulated content, or domains where AI output quality has compliance implications
• Published thinking or external contributions in AI engineering — talks, writing, open source
• Practical experience with MCP (Model Context Protocol) or equivalent agent integration standards

• Time off – 27 days holiday, plus 5 additional days off: 1 life event day, 2 volunteer days, 2 company‑wide wellbeing days (M‑Powered Weekend) and 8 bank holidays per year
• Health & Wellness — private medical insurance with Bupa, a medical cashback scheme, life insurance, gym membership & wellness resources through Wellhub and access to Spill — all in one mental health support
• Hybrid work offering – for most roles we collaborate in the office three days per week with the exception of coaches and instructors who collaborate in the office once a month
• Work‑from‑anywhere scheme – you'll have the opportunity to work from anywhere, up to 10 days per year
• Space to connect – beyond the desk, we make time for weekly catch‑ups, seasonal celebrations, and have a kitchen that’s always stocked!

We’re an equal opportunities employer. And proud of it. Every applicant and employee is afforded the same opportunities regardless of race, colour, ancestry, religion, sex, national origin, sexual orientation, age, citizenship, marital status, disability, gender, gender identity or expression, or veteran status. This will never change. Read our Equality, Diversity & Inclusion policy here.

Multiverse is…