AI / ML Engineer (Agentic AI Full-Stack Engineering)

Location: London (5 Days Onsite)
Client: J.P. Morgan Chase (JPMC)
Contract Duration: 14-16 Weeks
Pay: £410 - £430 per day (Inside IR35 / Umbrella(
Contract Type: Fixed-Term / Contract Opportunity

The Opportunity

We're partnering with JPMC to hire an experienced AI / ML Engineer with a strong full-stack Python background and proven expertise in building production-grade Agentic AI applications.
This is an exciting opportunity to work on cutting-edge AI initiatives, designing and delivering intelligent agent workflows that are scalable, reliable, secure, and enterprise-ready. You'll be responsible for building sophisticated multi-agent systems, integrating LLM capabilities into business processes, and ensuring robust governance, observability, and performance across the AI stack.

Key Responsibilities

• Design and develop multi-agent AI systems using frameworks such as Google ADK, LangChain, and LangGraph
• Build and maintain stateful workflows, orchestration layers, and agent decision-making processes
• Develop secure, scalable Python APIs and backend services that integrate with AI agents and enterprise systems
• Implement effective prompt engineering strategies, context management, memory handling, and system instructions
• Create reliable, structured outputs using JSON schemas and Pydantic validation
• Design and implement guardrails, fallback mechanisms, circuit breakers, and hallucination mitigation strategies
• Build observability frameworks, tracing tools, and evaluation-as-code capabilities to monitor agent behaviour and performance
• Collaborate with engineering and architecture teams to deploy AI solutions within cloud-native environments
• Ensure best practices across testing, security, scalability, and maintainability

Required Skills & Experience

Essential

• Strong commercial experience in Python development, backend engineering, and distributed systems
• Experience building APIs, microservices, and scalable production applications
• Hands-on experience with LLM platforms including OpenAI, Gemini, Claude, or similar
• Proven experience with LangChain, LangGraph, Google ADK, or related AI orchestration frameworks
• Strong understanding of agentic architectures, workflow orchestration, and AI application design
• Experience working with Google Cloud Platform (GCP)
• Google Professional Cloud Architect Certification (mandatory)
• Knowledge of containerisation technologies and cloud deployments (Docker, Kubernetes, CI/CD pipelines)
• Strong testing mindset, including unit, integration, and automated testing approaches for AI-driven systems
• Ability to design resilient systems that manage asynchronous events, state transitions, and complex decision paths

Desirable

• Experience implementing AI governance frameworks and responsible AI practices
• Exposure to observability tools, tracing frameworks, and AI evaluation platforms
• Experience working within large-scale enterprise environments, particularly financial services