CGEMJP00360221 - AI Engineer

CBSbutler Holdings Limited trading as CBSbutler; City Of London; Remote; GBP 96,000 - 126,000; Full time

Job summary

CBSbutler is seeking an experienced AI Engineer to build production-grade GenAI and Agentic AI products for a major public sector programme. You will design, implement and deliver AI solutions that combine LLMs, RAG and autonomous agent workflows with robust Python engineering and Azure technologies.

You will work in a product squad, turning complex requirements into secure, scalable AI systems, beyond prototypes, with strong emphasis on reliability, security and performance.

Qualifications

• Hands-on Python software engineering experience.
• Proven experience delivering production-grade GenAI and LLM applications.
• Experience designing and implementing Agentic AI workflows using LangGraph.
• Strong RAG architecture knowledge, including embeddings and semantic search.
• Experience with Azure AI services and cloud-based deployment.

Responsibilities

• Agentic AI: design and build multi-step agent workflows with tool calls and human-in-the-loop controls.
• GenAI & LLMs: develop applications using Python, prompt engineering, outputs and context management.
• RAG & Knowledge Retrieval: build end-to-end pipelines with embeddings, vector search and grounding.
• AI Quality & Assurance: implement evaluation, testing, guardrails to mitigate hallucinations.
• Azure AI Engineering: deploy solutions using Azure OpenAI and related services.
• Production Engineering: ensure robust, secure, observable backend services and APIs.

Skills

Python

GenAI

LLMs

Agentic AI workflows

AI engineering

Tools

LangGraph

Azure OpenAI

Azure AI Search

Cosmos DB

Redis

Key Vault

Job description

AI Engineer - Genai & Agentic AI

Rate: £600 per day inside ir35

Location: Remote

Contract: 6 months

Active SC security clearance is required for this role

Build production-grade AI that goes beyond the prompt. I'm looking for a hands-on AI Engineer to design, build and deliver next-generation Generative AI and Agentic AI products for a major public sector programme. This is an opportunity to work at the cutting edge of AI engineering, developing intelligent applications that combine LLMs, RAG and autonomous agent workflows with robust Python engineering and Microsoft Azure technologies.

You'll be working within a product squad, turning complex requirements into secure, scalable and production-ready AI solutions, not just prototypes or proofs of concept.

Responsibilities

• Agentic AI: Design and build multi-step agent workflows using LangGraph, including tool calling, state management, routing and human-in-the-loop controls.
• GenAI & LLMs: Develop LLM-powered applications using Python, prompt engineering, structured outputs and context management.
• RAG & Knowledge Retrieval: Build end-to-end RAG pipelines covering document ingestion, chunking, embeddings, vector search, reranking and evidence grounding.
• AI Quality & Assurance: Implement evaluation frameworks, automated testing, guardrails and techniques to mitigate hallucinations.
• Azure AI Engineering: Build and deploy solutions using Azure OpenAI, Azure AI Search, Azure AI Foundry and associated cloud services.
• Production Engineering: Design reliable applications with robust error handling, retries, recovery, observability, security and performance optimisation.

Required Experience

• Strong, hands-on Python software engineering experience.
• Proven experience delivering production-grade GenAI and LLM applications.
• Practical experience designing and implementing Agentic AI workflows using LangGraph.
• Strong RAG architecture knowledge, including embeddings, chunking and semantic/hybrid search.
• Experience with LLM evaluation, testing, grounding, guardrails and hallucination mitigation.
• Hands-on Azure AI experience, ideally including Azure OpenAI, Azure AI Search, Azure AI Foundry, Cosmos DB, Redis, Azure Monitor/Application Insights, Managed Identity and Key Vault.
• A solid software engineering mindset, with experience building APIs, automated tests and maintainable backend services.