Job description

• Build production-grade AI agents using RAG, semantic search, vector databases and AWS Bedrock.
• Drive AI systems through to production, covering deployment, observability, evaluation and optimisation.
• Define engineering standards across AWS and Infrastructure-as-Code.
• Implement AI guardrails including validation, hallucination detection and output filtering.
• Design and build MCP servers and integrations connecting AI agents with enterprise systems and tools.
• Evaluate and implement emerging agentic AI patterns, including multi-agent architectures and agent-to-agent communication.
• Mentor engineers and provide technical leadership across the AI development lifecycle.

• c. 7+ years' experience in Software Engineering, AI Engineering or a related discipline.
• Proven experience building and operating production-scale LLM and agentic AI solutions.
• Deep understanding of agentic architectures, tool use, reasoning, orchestration, memory and multi-agent systems.
• Strong experience with AWS, AWS Bedrock, LangChain, Strands or similar AI frameworks.
• Experience building RAG solutions, semantic search capabilities and applications powered by vector databases.
• Expertise in prompt engineering, context management and model evaluation.
• Strong communication skills and experience leading or mentoring engineering teams.
• Financial services experience highly regarded.

• Opportunity to shape the technical direction of a greenfield Applied AI function.
• Ownership of architecture and engineering standards for enterprise AI platforms.
• Exposure to cutting-edge agentic AI technologies and large-scale AI initiatives.

If you're interested in this role, click 'apply now' to forward an up-to-date copy of your CV, or call us now.

If this job isn't quite right for you, but you are looking for a new position, please contact us for a confidential discussion on your career.