Principal AI Platform Engineer

Working at CreateFuture CreateFuture is an AI-native consulting partner where people do work that matters and are supported to do it well. We work alongside organisations such as PayPal, adidas, NatWest, FanDuel and Money Saving Expert, building digital products and services that make a difference while always putting people first. We’re a team of creators. We write code, shape delivery, build go-to-market strategies, develop AI solutions and create the practices that support our people. We work side by side with our clients, challenging what’s not working and helping them to build the future. Our commitment to craft, quality, and culture has helped us scale to over 600 people in just a few years. Our UK Benefits • 35 days leave (including bank holidays). • Private medical insurance. • Enhanced parental and adoption leave. • Financial coaching + 5% pension match. • 40 hours of paid learning and development. View our full list of UK benefits. CreateFuture is a Great Place to Work-Certified™ company and has won Best Workplaces UK multiple years in a row. Join us on our journey. Let’s create tomorrow, together, today. About the role and team: You'll join our AI Platform Engineering team, which builds and runs the infrastructure connecting CreateFuture's engineers and client workloads to multiple LLM providers — from the inference control plane (the API gateway and routing layer for Anthropic, AWS Bedrock, OpenAI, and others) through to the orchestration and lifecycle tooling that turns individual AI integrations into a reusable 'capability marketplace', and the trust, safety, and governance controls that keep it all auditable as it scales. We're hiring across this team at several levels — Principal, Senior, and Mid: Principal engineers set technical direction for the platform and act as a trusted extension of the CreateFuture leadership team day to day; Senior engineers own delivery of key platform components, from the gateway through to orchestration; and Mid-level engineers build hands-on experience across the gateway, orchestration, and governance layers, with support from senior colleagues. What you'll be doing: • Build, run, and evolve the API gateway and routing layer connecting engineers and client workloads to multiple LLM providers (Anthropic, AWS Bedrock, OpenAI), including the failover and routing strategies you may need to defend in an incident. • Design and build orchestration and lifecycle management for AI capabilities and agents, including the tooling that lets teams register, discover, and reuse capabilities rather than rebuilding them. • Implement and maintain RBAC/OIDC access controls and disciplined API key lifecycle management across the platform. • Build caching layers and cost/latency optimisation strategies, and the adoption and reuse analytics that show whether the platform is actually being used. • Contribute to API design, versioning, and promotion workflows as capabilities move from experimental to production — with more senior engineers setting these standards and more junior engineers learning and applying them. • Bring a trust, safety, and governance lens to the platform, helping ensure the agents and capabilities running on it are well-governed, auditable, and safe to scale. We'd love to talk to you if you: • Are proficient in Python or Go, with production experience appropriate to your level — from hands-on delivery (Mid) through to setting technical direction (Principal). • Have production experience running API gateways (Kong preferred; Envoy or Apigee accepted), or are keen to build this experience. • Have integrated with, or are curious about, multiple LLM providers (Anthropic, AWS Bedrock, OpenAI), including failover and routing strategies you've had to defend under pressu