Agentic AI Engineer

Norton Blake; Greater London; Hybrid; GBP 124,000 - 207,000; Part time

Job summary

Norton Blake is seeking an experienced Agentic AI Engineer to design, build and deploy production-grade AI agents on Google Cloud Platform (GCP). The role requires hands-on Python development, LangChain/LangGraph, and MCP expertise to orchestrate multiple AI agents in scalable solutions.

You will collaborate with stakeholders to translate business requirements into technical designs, implement RAG and real-time workflows, and ensure security and compliance in production deployments.

Qualifications

• Hands-on experience building agentic AI solutions and multi-agent systems.
• Strong Python coding skills and integration with external services.
• Experience with LangChain, LangGraph and MCP for tool orchestration.

Responsibilities

• Identify and assess business use cases for AI agents delivering measurable value.
• Design, develop and deploy scalable AI agents on GCP.
• Build LLM-powered agents and conversational applications with real-time interactions.

Skills

Python coding

Prompt engineering

Generative AI

Communication

System design

Tools

LangChain

LangGraph

MCP

GCP

CI/CD

Kubernetes

Job description

Agentic AI Engineer | GCP, LangGraph & Python

Location: London - Hybrid 2 days a week

Duration: 6 Months - Extendable

Engagement: Contract

Role Overview

We are seeking an experienced, hands-on Agentic AI Engineer to design, build and deploy production-grade AI agents and multi-agent systems on Google Cloud Platform (GCP).

You will help identify opportunities for agentic AI, translate business requirements into technical solutions, and deliver secure, scalable applications. This role requires strong Python development skills, practical experience with LangChain, LangGraph and Model Context Protocol (MCP), and proven experience integrating multiple AI agents.

You will work closely with stakeholders, product teams and clients throughout the delivery lifecycle, from use case discovery and solution design through to deployment, monitoring and continuous improvement.

Key Responsibilities

• Identify and assess business use cases where AI agents can deliver measurable value, defining technical requirements and appropriate solution designs.
• Design, develop and deploy scalable, production-grade AI agents and multi-agent systems on GCP.
• Build LLM-powered agents and conversational AI applications capable of supporting complex workflows and real-time interactions.
• Develop agent workflows using LangChain and LangGraph, including orchestration, tool use, state management and coordination between agents.
• Use MCP to connect AI agents with relevant tools, data sources and services.
• Integrate agents with backend services, APIs and AI orchestration layers to support end-to-end business processes.
• Implement Retrieval-Augmented Generation (RAG) solutions using LLMs, vector databases and relevant enterprise data sources.
• Develop, test and refine prompts to improve the quality, consistency and reliability of agent responses.
• Implement AI guardrails covering safety, bias detection, hallucination controls and appropriate handling of sensitive information.
• Optimise application latency, response accuracy and user experience, particularly for real-time interactions.
• Establish monitoring, logging and analytics to track application performance, agent behaviour and operational issues.
• Deploy and maintain agent applications through CI/CD pipelines and Kubernetes.
• Ensure solutions meet security, compliance and responsible AI requirements.
• Collaborate with stakeholders, product teams and clients to clarify requirements, explain technical decisions and support successful delivery.

Essential Skills and Experience

• Strong hands-on experience designing and developing agentic AI solutions and multi-agent systems.
• Proven practical experience with LangChain, LangGraph and MCP.
• Strong Python coding skills, including building maintainable applications and integrating external services.
• Hands-on prompt engineering experience, with the ability to evaluate and improve LLM outputs.
• Experience integrating multiple AI agents, including managing their interactions, shared context and workflow execution.
• Practical experience with Generative AI, LLMs, vector databases and RAG integration.
• Experience building and deploying production-grade AI applications on GCP.
• Strong understanding of backend service integration, APIs and AI orchestration.
• Experience deploying applications using CI/CD pipelines and Kubernetes.
• Understanding of AI safety, bias detection, hallucination mitigation and responsible AI practices.
• Good knowledge of monitoring tools, logging and observability practices.
• Ability to troubleshoot and optimise AI applications for performance, reliability and response quality.
• Strong communication and stakeholder engagement skills, with the ability to translate business requirements into practical technical solutions.

What You Will Deliver

Secure, reliable and scalable AI agents that integrate with business systems, support valuable use cases and perform effectively in production. You will take ownership of the engineering required to move solutions from initial concept through to deployment and ongoing improvement.