Senior Developer, AI & Emerging Tech

The Senior Developer, AI & Emerging Tech is accountable for evolving the engineering and architecture of Burberry's shared agentic AI platform, including the orchestration layer, observability, agent registry, prompt engineering patterns, model selection and evaluation frameworks that underpin Burberry's enterprise agentic AI ambitions. Sitting within the centralised Architecture function under the Director, EA, the role will help shape the agentic AI platform strategy across IT and ensure the platform is scalable, secure, well-governed and aligned to business and technology priorities.

As a new capability for Burberry, the role carries a foundational responsibility to establish the engineering practices, tooling, documentation and knowledge base required to build and sustain this capability from the ground up.,

• Design, build and maintain the shared agentic platform services that domain-aligned and platform teams consume to deploy agents at enterprise scale.
• Own the agent platform engineering layer, ensuring agents are orchestrated, registered, monitored and governed to enterprise standards.
• Develop and maintain prompt engineering patterns, model selection frameworks, operations and evaluation methodologies.
• Serve as the interim centre of agentic development expertise; progressively transfer knowledge and patterns to domain teams
• Collaborate with Enterprise and Solution Architects to define agentic orchestration strategy and platform requirements and ensure platform engineering aligns with the enterprise reference architecture, design patterns and technology standards.
• Work with integration engineers to ensure seamless agent-to-system connectivity, supporting integration standards and patterns for agents and enabling agents to consume enterprise tools, systems and services through the governed integration layer.
• Work with data platform engineers to ensure agents can consume shared data infrastructure, including knowledge bases, real-time data feeds, data lineage and governed metrics, in a way that is reliable, performant, secure and aligned to data governance and AI ethics standards.
• Support domain-aligned product teams and Enterprise IT platform teams in the build and deployment of domain-specific and platform-specific agents, providing platform services, engineering guidance and pattern compliance review without owning the agents themselves.
• Establish and maintain clear documentation of agentic platform architecture, orchestration logic, agent registry schemas, evaluation frameworks and engineering standards.
• Define and enforce platform SLOs (service-level objectives) for the agentic layer, including orchestration latency, agent reliability and evaluation pipeline throughput.
• Continuously evaluate emerging agentic AI tooling, frameworks and architectural patterns; recommend adoption and conduct proof-of-concept validation where justified.
• 5+ years' experience in AI/ML engineering, platform engineering or software engineering roles. Hands-on experience designing, building and operating agentic AI systems, LLM-based platforms or multi agent orchestration frameworks on Azure, AWS or GCP (or similar).
• Core technical skills should include Python and modern software engineering practices; experience with LLM and agent development frameworks such as Lang Chain, Lang Graph, Semantic Kernel, Auto Gen or CrewAI; practical knowledge of RAG patterns, vector databases and embeddings; API design and integration using REST, event-driven and workflow-based patterns; CI/CD, automated testing and infrastructure-as-code; containerisation and deployment using Docker and Kubernetes;
  
  and hands-on experience with cloud AI services, preferably Microsoft Azure AI Foundry, Azure OpenAI, Microsoft Copilot Studio or equivalent services on AWS or GCP.
• Operational experience should include building production-grade services with monitoring, alerting, logging, incident management, release management, rollback procedures and service ownership disciplines, with the ability to define and operate SLOs for platform capabilities used by multiple teams.
• Strong understanding of enterprise integration patterns and how agents interact with systems, APIs and data sources.
• Practical familiarity with AI governance, risk and security controls, including model and prompt versioning, auditability, human-in-the-loop review, responsible AI guardrails, agent identity and access control, secrets management, data classification, data loss prevention, policy enforcement, bias…