AI Full-Stack Engineer (Agentic AI)

We're looking for an experienced AI Full-Stack Engineer to join a high-profile programme, building production-grade Agentic AI solutions for a global financial services organisation.

This role is ideal for a strong Python engineer with full-stack development experience who is passionate about applying the latest AI technologies to solve complex business problems. You'll design, build and deploy intelligent multi-agent systems, integrating Large Language Models (LLMs) into secure, scalable production environments.

Working as part of a collaborative engineering team, you'll help deliver reliable AI applications with a strong focus on performance, security, testing and observability.

Key Responsibilities

• Design, develop and deploy production-grade Agentic AI applications.
• Build multi-agent systems and stateful workflows using frameworks such as Google ADK, LangChain and LangGraph.
• Develop secure Python APIs and integrate external tools and services into AI workflows.
• Engineer effective prompts, manage conversational state and optimise context handling for LLM applications.
• Design structured outputs using JSON schemas and Pydantic models to ensure reliable responses.
• Implement guardrails, fallback mechanisms and safety controls to improve AI reliability and reduce hallucinations.
• Develop observability and monitoring solutions, including tracing, logging and evaluation frameworks for AI systems.
• Build scalable backend services and contribute to full-stack application development.
• Work closely with architects, product owners and engineering teams to deliver high-quality solutions.
• Write clean, well-tested code and contribute to CI/CD pipelines and automated deployments.

Skills & Experience

We're looking for candidates with:

• Strong commercial experience developing backend applications using Python.
• Experience building APIs, microservices and distributed systems.
• Hands-on experience with Large Language Models, including OpenAI, Gemini or Claude APIs.
• Experience using AI orchestration frameworks such as LangChain, LangGraph or similar.
• Strong understanding of Google Cloud Platform (GCP) services and architecture.
• Experience building and deploying cloud-native applications.
• Knowledge of containers, Docker, Kubernetes and CI/CD pipelines.
• Experience writing unit, integration and automated tests.
• Excellent problem-solving skills and a systems-thinking approach to software design.
• Google Professional Cloud Architect Certification (essential).
• Experience developing production-grade AI or LLM-enabled applications.
• Ability to work onsite in London five days per week.
• Experience with Agentic AI architectures.
• Knowledge of asynchronous workflows and event-driven systems.
• Exposure to AI evaluation frameworks and prompt testing.
• Financial services experience would be advantageous.