About this role
Salary: £? - ? per year
Requirements
- 8+ years of experience in backend or platform engineering, architecture, or similar enterprise-scale delivery roles.
- Commercial experience delivering AI solutions into production within the past three years.
- Strong systems-thinking skills, including designing and evolving complex systems for resilience, scalability, high availability, maintainability, and performance.
- Proficiency in Python and React, strong coding fundamentals and architectural judgment, and hands-on experience delivering complex systems; Java proficiency may also be required.
- Strong hands-on skills in microservice development, Kubernetes, CI/CD, and quality automation.
- Strong understanding of LLM and agent architecture patterns, including task decomposition, planning, tool use or function calling, context management, memory design, execution loops, failure handling, and safety guardrails.
- Hands-on experience with LangChain, LangGraph, or equivalent orchestration frameworks.
- Familiarity with AI developer tools such as Claude Code, Codex, Cursor, or Copilot.
- Cloud-native engineering experience and a platform mindset; Google Cloud experience is an example.
- Strong microservice design and development skills, including experience with databases, message brokers, and CI/CD toolkits.
- Certifications in cloud platforms, architecture, or programming are a plus.
- Kubernetes knowledge or certification, and familiarity with ecosystem tools such as Google Cloud Pub/Sub and Spring Gateway or equivalents, are a plus.
- Contributions to engineering communities are a plus.
Responsibilities
- We need you to lead the architecture and hands-on implementation of an AI agent platform, including task orchestration, tool invocation, context and session management, memory, and multi-agent collaboration.
- Translate emerging model capabilities into reusable platform components, such as SDKs, services, templates, and guardrails, so teams can adopt them safely and quickly.
- Build production implementations for complex engineering scenarios, optimizing for reliability, latency, and cost.
- Embed AI capabilities in business workflows, including AI-assisted agents, AI evaluation, and natural-language-to-SQL generation.
- Establish quality and measurement practices for AI features, covering accuracy, coverage, drift, prompt and tool regression, and cost.
- Design and implement a knowledge layer that grounds AI responses in enterprise information, including RAG, GraphRAG, and knowledge graph design and integration.
- Develop indexing strategies, evaluate retrieval, tune relevance, and govern enterprise knowledge usage through permissions, lineage, and auditability.
- Deliver production-grade full-stack solutions using Python backend microservices and React frontend interfaces, applying secure engineering practices and sound system design.
- Build and operate cloud-native services using CI/CD, DevSecOps, test automation, environment management, and observability through metrics, logs, and traces.
- Drive high availability and operational readiness, and collaborate with Product, Engineering, QA, and Operations to standardize, productionize, and continuously improve platform capabilities.
- Mentor engineers and improve delivery maturity using practical engineering metrics such as DORA.
Technologies
- AI
- AI Agents
- Backend
- CI/CD
- Claude Code
- Cloud
- Copilot
- Cursor
- DevSecOps
- Frontend
- Java
- Kubernetes
- LLM
- Python
- RAG
- React
- SQL
- Spring
- microservices
- DevOps
- GCP
- Security
- UX UI Design
More
Were hiring an AI Agent Developer to own the technical delivery of an enterprise AI agent and AI-native engineering platform that supports task automation for our Finance Operations business users. The role combines architectural design with hands-on, full-stack engineering, integrating large language models, AI agents, and knowledge augmentation from requirements and design through coding, testing, and environment orchestration. Our aim is to deliver a secure, scalable platform that runs reliably in production, is adopted across teams, improves delivery speed and quality, and supports a team culture of continuous learning and blameless accountability.
last updated 46 week of 2026