Lead AI Engineer

NXA Talent LTD; City Of London; Hybrid; GBP 90,000 - 130,000; Full time

Job summary

NXA Talent LTD is seeking an experienced AI Engineer in London with strong expertise in Azure OpenAI, LangGraph, and multi-agent architectures. The role focuses on designing and delivering production-grade AI solutions within a large-scale retail environment, with a hybrid working arrangement in London.

You will design agentic AI systems, build scalable microservices, and lead the deployment of AI services to production.

Qualifications

• Proven experience designing and delivering production-grade AI solutions.

Responsibilities

• Design and develop Agentic AI solutions with multi-step reasoning and autonomous action.
• Architect multi agent systems and scalable AI microservices.
• Build AI applications using Python and Azure OpenAI technologies.
• Develop RAG architectures and integrate vector search solutions.
• Implement orchestration workflows using Semantic Kernel and LangGraph.
• Integrate enterprise systems, APIs and tools using MCP and similar frameworks.
• Establish AI governance, security, safety and responsible AI practices.
• Lead the deployment of AI services into production environments.
• Collaborate with architects, product teams and stakeholders to deliver AI-driven solutions.
• Optimize performance, scalability, cost and latency of LLM-based applications.

Skills

AI architecture

Python development

Production-grade AI

Cloud AI

REST API design

Troubleshooting production

Tools

Azure OpenAI

Azure AI Foundry

Azure AI Search

Semantic Kernel

LangGraph

MCP (Model Context Protocol)

Docker

Kubernetes

MLOps

LLMOps

Vector databases

Embeddings

Semantic search

Job description

AI Engineer

• Leading UK Retailer
• London (Hybrid Working)
• 12 Months
• Inside IR35

This is an exciting opportunity to play a key role in shaping and delivering next generation AI capabilities within a large scale retail environment.

Role Responsibilities

• Design and develop Agentic AI solutions capable of multi-step reasoning, planning, and autonomous action execution.
• Architect multi agent systems, orchestration patterns, and scalable AI microservices.
• Build AI applications using Python and Azure OpenAI technologies.
• Develop RAG architectures and integrate vector search solutions.
• Implement orchestration workflows using Semantic Kernel and LangGraph.
• Integrate enterprise systems, APIs, and tools using MCP and similar frameworks.
• Establish AI governance, security, safety, and responsible AI practices.
• Lead the implementation and deployment of AI services into production environments.
• Collaborate with architects, product teams, and business stakeholders to deliver AI driven solutions.
• Optimise performance, scalability, cost, and latency of LLM based applications.

Experience Required

• Proven experience designing and delivering production grade AI and Generative AI solutions.
• Strong expertise in Azure OpenAI, Azure AI Foundry, Azure AI Search, Semantic Kernel, and LangGraph.
• Experience building multi agent architectures, RAG solutions, and complex orchestration workflows.
• Strong Python development skills with experience building scalable microservices.
• Knowledge of MCP (Model Context Protocol) and AI tool integration frameworks.
• Experience with event driven architectures, REST APIs, Docker, Kubernetes, MLOps, and LLMOps.
• Solid understanding of vector databases, embeddings, semantic search, and relational/NoSQL databases.
• Experience defining AI governance frameworks, coding standards, and best practices.
• Ability to troubleshoot and support AI solutions in production environments.