About

We are maintaining and enhancing our Generative AI Platform that enables our entire organisation to leverage Generative AI safely, efficiently and at scale. As a AI Engineer, you will be the force multiplier, moving beyond building end-user applications to developing robust, centralised services that power all internal GenAI product squads. You will be instrumental in designing and implementing our award winning Generative AI Platform Model Orchestration Layer, RAG infrastructure, communications layer, agentic layer and centralised governance/safety guardrails etc. This is a hybrid role, typically working 1 day per week at our Citigen office in London. Here's a taste of what you'll be doing Design, build, and maintain the highly reliable Model Serving Layer (Gateways, load balancing, caching, throttling) for low-latency access to LLMs and other generative models. Engineer and maintain production-ready Vector Database and Retrieval-Augmented Generation (RAG) infrastructure, including high-throughput indexing pipelines and efficient retrieval strategies for enterprise data. Develop and manage a standardised, secure Agent Framework/SDK (e.g., based on LangGraph or a custom library) that promotes consistency and maintainability across all agents built from the platform. Implement robust mechanisms for cost tracking, monitoring, and precise cost allocation/chargebacks per squad, alongside implementing rate-limiting and budget controls. Systematically benchmark, curate, and integrate the most cost-effective and performant models for distinct use cases. Build and maintain scalable, secure infrastructure and data pipelines for custom model fine-tuning requested by product teams. Architect and deploy platform-level safety filters (e.g., toxicity, PII masking, jailbreak prevention) that are enforced across all