Staff Software Engineer

We are recruiting for a Staff Software Engineer (AI) to help design, build and evolve production-grade agentic AI systems. This is a strategic, hands-on engineering leadership role focused on integrating Large Language Models into scalable, secure, reliable and observable architectures. This is an individual contributor leadership role with no direct line management responsibility. You will help move our agentic AI capabilities beyond experimentation and into dependable products that operate safely and effectively at scale across our global marketplace. Working closely with software engineers, machine learning engineers, data scientists, product managers, analysts and technical leaders, you will shape how we build, test, deploy, monitor and govern AI-powered systems. Success in this role will depend as much on influence and communication as on technical depth. You will need to create alignment across teams, explain complex concepts clearly, and help others make confident, pragmatic decisions. Your responsibilities - Design, architect and deliver agentic, LLM-powered systems in AWS, ensuring production readiness, scalability, reliability and security. - Provide technical leadership to evolve AI solutions from experimentation into robust, observable and maintainable products. - Collaborate cross-functionally with product, engineering, ML and data teams to align technical decisions with user needs, business priorities and long-term platform strategy. - Define and drive engineering standards, reusable patterns, tools and best practices for building responsible, consistent and scalable AI systems. - Lead large-scale implementation and deployment, ensuring excellence across testing, monitoring, evaluation, guardrails and operational support, while clearly communicating architectural decisions and mentoring engineers to raise overall engineering quality. - Strong Staff-level software engineering background with expertise in Python and at least one of Java, TypeScript or .NET, and a proven track record delivering production-grade systems. - Experience designing, building and operating distributed systems on AWS (or similar cloud platforms), including secure development, data protection, compliance and enterprise architecture principles. - Hands-on experience integrating LLMs into production, including use of APIs (e.g. OpenAI, Bedrock), prompt orchestration, tool usage and interaction patterns. - Expertise in AI system design including state management, memory strategies, evaluation approaches, guardrails, observability and performance optimisation for LLM-powered systems. - Strong communication and influencing skills, with experience mentoring engineers and driving high standards across teams while engaging both technical and non-technical stakeholders.