AI Full-Stack Engineer

We are seeking an experienced AI Full-Stack Engineer to join a high-profile project within JPMC, focused on designing and delivering production-grade Agentic AI solutions. This role is ideal for a strong Python engineer with deep experience in modern AI frameworks, cloud architecture, and scalable Back End systems.

The successful candidate will play a key role in developing intelligent multi-agent applications, integrating LLMs into enterprise environments, and ensuring reliability, observability, and governance across AI-powered workflows., * Design and build multi-agent systems and stateful AI workflows using frameworks such as Google ADK, LangChain, and LangGraph

• Develop secure and scalable Python APIs and services that integrate with AI agents and enterprise systems
• Implement tool-calling capabilities and API integrations to enable agents to interact with external applications and data sources
• Engineer effective prompts, context management, memory systems, and workflow orchestration for LLM-powered applications
• Create and maintain structured AI outputs using JSON schemas and Pydantic validation
• Develop AI safety mechanisms including guardrails, fallback logic, hallucination mitigation, and circuit-breaker controls
• Establish observability and evaluation frameworks, including agent tracing, monitoring, and automated prompt testing
• Collaborate with architects, engineers, and stakeholders to deploy AI solutions into production environments
• Contribute to CI/CD pipelines, testing strategies, and cloud-native deployment practices

• Strong commercial experience with Python development, Back End engineering, APIs, microservices, and distributed system design
• Hands-on experience working with LLM APIs such as Gemini, OpenAI, and Claude
• Experience using AI orchestration frameworks including LangChain, LangGraph, or similar technologies
• Strong understanding of Google Cloud Platform (GCP) services and cloud-native application development
• Google Professional Cloud Architect certification (essential)
• Experience with containerisation technologies and modern deployment practices (Docker, Kubernetes, CI/CD)
• Strong testing mindset, including unit, integration, and automated testing approaches for AI-driven systems
• Knowledge of asynchronous processing, workflow orchestration, state management, and event-driven architectures
• Ability to design resilient, scalable, and maintainable solutions within enterprise environments

Desirable Experience

• PhD in Machine Learning, Artificial Intelligence, Computer Science, or a related discipline
• Experience training, fine-tuning, or pre-training foundation models
• Experience working with large-scale GPU infrastructure and distributed training environments
• Strong mathematical background, including algorithm development and optimisation
• Previous experience delivering enterprise-grade Agentic AI solutions in highly regulated environments